AI researchers have long focused on poker-like games as a testbed for environments characterized by multi-player dynamics, imperfect information, and reasoning under uncertainty. While recent breakthroughs have matched elite human play at no-limit Texas hold'em, the multi-player dynamics are subdued: most hands converge quickly with only two players engaged through multiple rounds of bidding. In this paper, we present Solly, the first AI agent to achieve elite human play in reduced-format Liar's Poker, a game characterized by extensive multi-player engagement. We trained Solly using self-play with a model-free, actor-critic, deep reinforcement learning algorithm. Solly played at an elite human level as measured by win rate (won over 50% of hands) and equity (money won) in heads-up and multi-player Liar's Poker. Solly also outperformed large language models (LLMs), including those with reasoning abilities, on the same metrics. Solly developed novel bidding strategies, randomized play effectively, and was not easily exploitable by world-class human players.
Analog/mixed-signal circuits are key for interfacing electronics with the physical world. Their design, however, remains a largely handcrafted process, resulting in long and error-prone design cycles. While the recent rise of AI-based reinforcement learning and generative AI has created new techniques to automate this task, the need for many time-consuming simulations is a critical bottleneck hindering the overall efficiency. Furthermore, the lack of explainability of the resulting design solutions hampers widespread adoption of the tools. To address these issues, a novel agentic AI framework for sample-efficient and explainable analog circuit sizing is presented. It employs a multi-agent workflow where specialized Large Language Model (LLM)-based agents collaborate to interpret the circuit topology, to understand the design goals, and to iteratively refine the circuit's design parameters towards the target goals with human-interpretable reasoning. The adaptive simulation strategy creates an intelligent control that yields a high sample efficiency. The AnaFlow framework is demonstrated for two circuits of varying complexity and is able to complete the sizing task fully automatically, differently from pure Bayesian optimization and reinforcement learning approaches. The system learns from its optimization history to avoid past mistakes and to accelerate convergence. The inherent explainability makes this a powerful tool for analog design space exploration and a new paradigm in analog EDA, where AI agents serve as transparent design assistants.
Agents are now used widely in the process of software development, but building production-ready software engineering agents is a complex task. Deploying software agents effectively requires flexibility in implementation and experimentation, reliable and secure execution, and interfaces for users to interact with agents. In this paper, we present the OpenHands Software Agent SDK, a toolkit for implementing software development agents that satisfy these desiderata. This toolkit is a complete architectural redesign of the agent components of the popular OpenHands framework for software development agents, which has 64k+ GitHub stars. To achieve flexibility, we design a simple interface for implementing agents that requires only a few lines of code in the default case, but is easily extensible to more complex, full-featured agents with features such as custom tools, memory management, and more. For security and reliability, it delivers seamless local-to-remote execution portability, integrated REST/WebSocket services. For interaction with human users, it can connect directly to a variety of interfaces, such as visual workspaces (VS Code, VNC, browser), command-line interfaces, and APIs. Compared with existing SDKs from OpenAI, Claude, and Google, OpenHands uniquely integrates native sandboxed execution, lifecycle control, model-agnostic multi-LLM routing, and built-in security analysis. Empirical results on SWE-Bench Verified and GAIA benchmarks demonstrate strong performance. Put together, these elements allow the OpenHands Software Agent SDK to provide a practical foundation for prototyping, unlocking new classes of custom applications, and reliably deploying agents at scale.
Large language models (LLMs) achieve strong performance across benchmarks--from knowledge quizzes and math reasoning to web-agent tasks--but these tests occur in static settings, lacking real dynamics and uncertainty. Consequently, they evaluate isolated reasoning or problem-solving rather than decision-making under uncertainty. To address this, we introduce LiveTradeBench, a live trading environment for evaluating LLM agents in realistic and evolving markets. LiveTradeBench follows three design principles: (i) Live data streaming of market prices and news, eliminating dependence on offline backtesting and preventing information leakage while capturing real-time uncertainty; (ii) a portfolio-management abstraction that extends control from single-asset actions to multi-asset allocation, integrating risk management and cross-asset reasoning; and (iii) multi-market evaluation across structurally distinct environments--U.S. stocks and Polymarket prediction markets--differing in volatility, liquidity, and information flow. At each step, an agent observes prices, news, and its portfolio, then outputs percentage allocations that balance risk and return. Using LiveTradeBench, we run 50-day live evaluations of 21 LLMs across families. Results show that (1) high LMArena scores do not imply superior trading outcomes; (2) models display distinct portfolio styles reflecting risk appetite and reasoning dynamics; and (3) some LLMs effectively leverage live signals to adapt decisions. These findings expose a gap between static evaluation and real-world competence, motivating benchmarks that test sequential decision making and consistency under live uncertainty.
The increasing complexity of machine learning models and the proliferation of diverse hardware architectures (CPUs, GPUs, accelerators) make achieving optimal performance a significant challenge. Heterogeneity in instruction sets, specialized kernel requirements for different data types and model features (e.g., sparsity, quantization), and architecture-specific optimizations complicate performance tuning. Manual optimization is resource-intensive, while existing automatic approaches often rely on complex hardware-specific heuristics and uninterpretable intermediate representations, hindering performance portability. We introduce PerfLLM, a novel automatic optimization methodology leveraging Large Language Models (LLMs) and Reinforcement Learning (RL). Central to this is PerfDojo, an environment framing optimization as an RL game using a human-readable, mathematically-inspired code representation that guarantees semantic validity through transformations. This allows effective optimization without prior hardware knowledge, facilitating both human analysis and RL agent training. We demonstrate PerfLLM's ability to achieve significant performance gains across diverse CPU (x86, Arm, RISC-V) and GPU architectures.
Large language models (LLMs) have shown strong capabilities in software engineering tasks, yet most existing LLM-based SWE-Agents mainly tackle well-defined problems using conventional methods, often overlooking alternative or innovative solutions beyond their predefined frameworks. This limitation is evident in open-world software environments, where emerging challenges transcend established paradigms. We propose U2F (Unknown Unknowns to Functional solutions), a cognitive-inspired, uncertainty-embracing multi-agent framework that systematically surfaces "Unknown Unknowns" - novel solution pathways absent from initial formulations but holding innovative potential. U2F consists of two key components: (1) a Discovery-Exploration-Integration agent system for uncovering and synthesizing potential solutions, and (2) cognitive enhancement mechanisms across three dimensions: cross-domain analogical reasoning, reverse thinking, and external validation, which strategically reframe and extend conventional solution boundaries. Applied to 218 real-world software enabler stories curated from authentic engineering tasks, U2F achieved notable improvements: human experts reported a 14 percent increase in overall novelty, 51 percent improvement in semantic novelty, and stable feasibility (4.02/5.0), corroborated by an LLM-based evaluator. These results highlight the potential of embracing uncertainty as a catalyst for innovation in software engineering.
Memory systems are key components that enable AI systems such as LLMs and AI agents to achieve long-term learning and sustained interaction. However, during memory storage and retrieval, these systems frequently exhibit memory hallucinations, including fabrication, errors, conflicts, and omissions. Existing evaluations of memory hallucinations are primarily end-to-end question answering, which makes it difficult to localize the operational stage within the memory system where hallucinations arise. To address this, we introduce the Hallucination in Memory Benchmark (HaluMem), the first operation level hallucination evaluation benchmark tailored to memory systems. HaluMem defines three evaluation tasks (memory extraction, memory updating, and memory question answering) to comprehensively reveal hallucination behaviors across different operational stages of interaction. To support evaluation, we construct user-centric, multi-turn human-AI interaction datasets, HaluMem-Medium and HaluMem-Long. Both include about 15k memory points and 3.5k multi-type questions. The average dialogue length per user reaches 1.5k and 2.6k turns, with context lengths exceeding 1M tokens, enabling evaluation of hallucinations across different context scales and task complexities. Empirical studies based on HaluMem show that existing memory systems tend to generate and accumulate hallucinations during the extraction and updating stages, which subsequently propagate errors to the question answering stage. Future research should focus on developing interpretable and constrained memory operation mechanisms that systematically suppress hallucinations and improve memory reliability.
Agentic AI systems and Physical or Embodied AI systems have been two key research verticals at the forefront of Artificial Intelligence and Robotics, with Model Context Protocol (MCP) increasingly becoming a key component and enabler of agentic applications. However, the literature at the intersection of these verticals, i.e., Agentic Embodied AI, remains scarce. This paper introduces an MCP server for analyzing ROS and ROS 2 bags, allowing for analyzing, visualizing and processing robot data with natural language through LLMs and VLMs. We describe specific tooling built with robotics domain knowledge, with our initial release focused on mobile robotics and supporting natively the analysis of trajectories, laser scan data, transforms, or time series data. This is in addition to providing an interface to standard ROS 2 CLI tools ("ros2 bag list" or "ros2 bag info"), as well as the ability to filter bags with a subset of topics or trimmed in time. Coupled with the MCP server, we provide a lightweight UI that allows the benchmarking of the tooling with different LLMs, both proprietary (Anthropic, OpenAI) and open-source (through Groq). Our experimental results include the analysis of tool calling capabilities of eight different state-of-the-art LLM/VLM models, both proprietary and open-source, large and small. Our experiments indicate that there is a large divide in tool calling capabilities, with Kimi K2 and Claude Sonnet 4 demonstrating clearly superior performance. We also conclude that there are multiple factors affecting the success rates, from the tool description schema to the number of arguments, as well as the number of tools available to the models. The code is available with a permissive license at https://github.com/binabik-ai/mcp-rosbags.
Retrieval-augmented generation (RAG) enhances large language models (LLMs) with retrieved context but often suffers from downgraded prefill performance as modern applications demand longer and more complex inputs. Existing caching techniques either preserve accuracy with low cache reuse or improve reuse at the cost of degraded reasoning quality. We present RAGBoost, an efficient RAG system that achieves high cache reuse without sacrificing accuracy through accuracy-preserving context reuse. RAGBoost detects overlapping retrieved items across concurrent sessions and multi-turn interactions, using efficient context indexing, ordering, and de-duplication to maximize reuse, while lightweight contextual hints maintain reasoning fidelity. It integrates seamlessly with existing LLM inference engines and improves their prefill performance by 1.5-3X over state-of-the-art methods, while preserving or even enhancing reasoning accuracy across diverse RAG and agentic AI workloads. Our code is released at: https://github.com/Edinburgh-AgenticAI/RAGBoost.
As the "agentic web" takes shape-billions of AI agents (often LLM-powered) autonomously transacting and collaborating-trust shifts from human oversight to protocol design. In 2025, several inter-agent protocols crystallized this shift, including Google's Agent-to-Agent (A2A), Agent Payments Protocol (AP2), and Ethereum's ERC-8004 "Trustless Agents," yet their underlying trust assumptions remain under-examined. This paper presents a comparative study of trust models in inter-agent protocol design: Brief (self- or third-party verifiable claims), Claim (self-proclaimed capabilities and identity, e.g. AgentCard), Proof (cryptographic verification, including zero-knowledge proofs and trusted execution environment attestations), Stake (bonded collateral with slashing and insurance), Reputation (crowd feedback and graph-based trust signals), and Constraint (sandboxing and capability bounding). For each, we analyze assumptions, attack surfaces, and design trade-offs, with particular emphasis on LLM-specific fragilities-prompt injection, sycophancy/nudge-susceptibility, hallucination, deception, and misalignment-that render purely reputational or claim-only approaches brittle. Our findings indicate no single mechanism suffices. We argue for trustless-by-default architectures anchored in Proof and Stake to gate high-impact actions, augmented by Brief for identity and discovery and Reputation overlays for flexibility and social signals. We comparatively evaluate A2A, AP2, ERC-8004 and related historical variations in academic research under metrics spanning security, privacy, latency/cost, and social robustness (Sybil/collusion/whitewashing resistance). We conclude with hybrid trust model recommendations that mitigate reputation gaming and misinformed LLM behavior, and we distill actionable design guidelines for safer, interoperable, and scalable agent economies.
In recent years, Large Language Models (LLMs) have achieved remarkable progress in automated code generation. In real-world software engineering, the growing demand for rapid iteration and continuous delivery underscores the importance of project-level code generation, where LLMs are expected to generate complete software projects directly from complex user requirements. Although existing studies have made initial explorations, they still face key limitations, including unrealistic datasets and unreliable evaluation metrics that fail to reflect real-world complexity, the semantic gap between human-written requirements and machine-interpretable structures, and difficulties in managing hierarchical dependencies and maintaining quality throughout the generation process. To address these limitations, we first introduce CodeProjectEval, a project-level code generation dataset built from 18 real-world repositories with 12.7 files and 2,388.6 lines of code per task on average, supplemented with documentation and executable test cases for automatic evaluation. We further propose ProjectGen, a multi-agent framework that decomposes projects into architecture design, skeleton generation, and code filling stages with iterative refinement and memory-based context management. Within this framework, we introduce the Semantic Software Architecture Tree (SSAT), a structured and semantically rich representation that effectively bridges user requirements and source code implementation. Experiments show that ProjectGen achieves state-of-the-art performance, passing 52/124 test cases on the small-scale project-level code generation dataset DevBench, a 57% improvement over the baseline approaches, and 310 test cases on CodeProjectEval, representing an improvement of roughly tenfold compared to the baselines.
The deployment of large language models (LLMs) in automated negotiation has set a high performance benchmark, but their computational cost and data privacy requirements render them unsuitable for many privacy-sensitive, on-device applications such as mobile assistants, embodied AI agents or private client interactions. While small language models (SLMs) offer a practical alternative, they suffer from a significant performance gap compared to LLMs in playing emotionally charged complex personas, especially for credit negotiation. This paper introduces EQ-Negotiator, a novel framework that bridges this capability gap using emotional personas. Its core is a reasoning system that integrates game theory with a Hidden Markov Model(HMM) to learn and track debtor emotional states online, without pre-training. This allows EQ-Negotiator to equip SLMs with the strategic intelligence to counter manipulation while de-escalating conflict and upholding ethical standards. Through extensive agent-to-agent simulations across diverse credit negotiation scenarios, including adversarial debtor strategies like cheating, threatening, and playing the victim, we show that a 7B parameter language model with EQ-Negotiator achieves better debt recovery and negotiation efficiency than baseline LLMs more than 10 times its size. This work advances persona modeling from descriptive character profiles to dynamic emotional architectures that operate within privacy constraints. Besides, this paper establishes that strategic emotional intelligence, not raw model scale, is the critical factor for success in automated negotiation, paving the way for effective, ethical, and privacy-preserving AI negotiators that can operate on the edge.
In this study, a modular, data-free pipeline for multi-label intention recognition is proposed for agentic AI applications in transportation. Unlike traditional intent recognition systems that depend on large, annotated corpora and often struggle with fine-grained, multi-label discrimination, our approach eliminates the need for costly data collection while enhancing the accuracy of multi-label intention understanding. Specifically, the overall pipeline, named DMTC, consists of three steps: 1) using prompt engineering to guide large language models (LLMs) to generate diverse synthetic queries in different transport scenarios; 2) encoding each textual query with a Sentence-T5 model to obtain compact semantic embeddings; 3) training a lightweight classifier using a novel online focal-contrastive (OFC) loss that emphasizes hard samples and maximizes inter-class separability. The applicability of the proposed pipeline is demonstrated in an agentic AI application in the maritime transportation context. Extensive experiments show that DMTC achieves a Hamming loss of 5.35% and an AUC of 95.92%, outperforming state-of-the-art multi-label classifiers and recent end-to-end SOTA LLM-based baselines. Further analysis reveals that Sentence-T5 embeddings improve subset accuracy by at least 3.29% over alternative encoders, and integrating the OFC loss yields an additional 0.98% gain compared to standard contrastive objectives. In conclusion, our system seamlessly routes user queries to task-specific modules (e.g., ETA information, traffic risk evaluation, and other typical scenarios in the transportation domain), laying the groundwork for fully autonomous, intention-aware agents without costly manual labelling.
Recent advances in multi-modal Large Language Models (M-LLMs) have demonstrated a powerful ability to synthesize implicit information from disparate sources, including images and text. These resourceful data from social media also introduce a significant and underexplored privacy risk: the inference of sensitive personal attributes from seemingly daily media content. However, the lack of benchmarks and comprehensive evaluations of state-of-the-art M-LLM capabilities hinders the research of private attribute profiling on social media. Accordingly, we propose (1) PRISM, the first multi-modal, multi-dimensional and fine-grained synthesized dataset incorporating a comprehensive privacy landscape and dynamic user history; (2) an Efficient evaluation framework that measures the cross-modal privacy inference capabilities of advanced M-LLM. Specifically, PRISM is a large-scale synthetic benchmark designed to evaluate cross-modal privacy risks. Its key feature is 12 sensitive attribute labels across a diverse set of multi-modal profiles, which enables targeted privacy analysis. These profiles are generated via a sophisticated LLM agentic workflow, governed by a prior distribution to ensure they realistically mimic social media users. Additionally, we propose a Multi-Agent Inference Framework that leverages a pipeline of specialized LLMs to enhance evaluation capabilities. We evaluate the inference capabilities of six leading M-LLMs (Qwen, Gemini, GPT-4o, GLM, Doubao, and Grok) on PRISM. The comparison with human performance reveals that these MLLMs significantly outperform in accuracy and efficiency, highlighting the threat of potential privacy risks and the urgent need for robust defenses.
Large language models (LLMs) excel in generating fluent utterances but can lack reliable grounding in verified information. At the same time, knowledge-graph-based fact-checkers deliver precise and interpretable evidence, yet suffer from limited coverage or latency. By integrating LLMs with knowledge graphs and real-time search agents, we introduce a hybrid fact-checking approach that leverages the individual strengths of each component. Our system comprises three autonomous steps: 1) a Knowledge Graph (KG) Retrieval for rapid one - hop lookups in DBpedia, 2) an LM-based classification guided by a task-specific labeling prompt, producing outputs with internal rule-based logic, and 3) a Web Search Agent invoked only when KG coverage is insufficient. Our pipeline achieves an F1 score of 0.93 on the FEVER benchmark on the Supported/Refuted split without task- specific fine - tuning. To address Not enough information cases, we conduct a targeted reannotation study showing that our approach frequently uncovers valid evidence for claims originally labeled as Not Enough Information (NEI), as confirmed by both expert annotators and LLM reviewers. With this paper, we present a modular, opensource fact-checking pipeline with fallback strategies and generalization across datasets.
The engineering design process often demands expertise from multiple domains, leading to complex collaborations and iterative refinements. Traditional methods can be resource-intensive and prone to inefficiencies. To address this, we formalize the engineering design process through a multi-agent AI framework that integrates structured design and review loops. The framework introduces specialized knowledge-driven agents that collaborate to generate and refine design candidates. As an exemplar, we demonstrate its application to the aerodynamic optimization of 4-digit NACA airfoils. The framework consists of three key AI agents: a Graph Ontologist, a Design Engineer, and a Systems Engineer. The Graph Ontologist employs a Large Language Model (LLM) to construct two domain-specific knowledge graphs from airfoil design literature. The Systems Engineer, informed by a human manager, formulates technical requirements that guide design generation and evaluation. The Design Engineer leverages the design knowledge graph and computational tools to propose candidate airfoils meeting these requirements. The Systems Engineer reviews and provides feedback both qualitative and quantitative using its own knowledge graph, forming an iterative feedback loop until a design is validated by the manager. The final design is then optimized to maximize performance metrics such as the lift-to-drag ratio. Overall, this work demonstrates how collaborative AI agents equipped with structured knowledge representations can enhance efficiency, consistency, and quality in the engineering design process.
Large Language Models (LLMs) have substantially influenced various software engineering tasks. Indeed, in the case of software refactoring, traditional LLMs have shown the ability to reduce development time and enhance code quality. However, these LLMs often rely on static, detailed instructions for specific tasks. In contrast, LLM-based agents can dynamically adapt to evolving contexts and autonomously make decisions by interacting with software tools and executing workflows. In this paper, we explore the potential of LLM-based agents in supporting refactoring activities. Specifically, we introduce RefAgent, a multi-agent LLM-based framework for end-to-end software refactoring. RefAgent consists of specialized agents responsible for planning, executing, testing, and iteratively refining refactorings using self-reflection and tool-calling capabilities. We evaluate RefAgent on eight open-source Java projects, comparing its effectiveness against a single-agent approach, a search-based refactoring tool, and historical developer refactorings. Our assessment focuses on: (1) the impact of generated refactorings on software quality, (2) the ability to identify refactoring opportunities, and (3) the contribution of each LLM agent through an ablation study. Our results show that RefAgent achieves a median unit test pass rate of 90%, reduces code smells by a median of 52.5%, and improves key quality attributes (e.g., reusability) by a median of 8.6%. Additionally, it closely aligns with developer refactorings and the search-based tool in identifying refactoring opportunities, attaining a median F1-score of 79.15% and 72.7%, respectively. Compared to single-agent approaches, RefAgent improves the median unit test pass rate by 64.7% and the median compilation success rate by 40.1%. These findings highlight the promise of multi-agent architectures in advancing automated software refactoring.
Empathy is a critical factor in fostering positive user experiences in conversational AI. While models can display empathy, it is often generic rather than tailored to specific tasks and contexts. In this work, we introduce a novel framework for developing and evaluating context-specific empathetic large language models (LLMs). We first analyze a real-world conversational dataset consisting of 672 multi-turn conversations across 8 tasks, revealing significant differences in terms of expected and experienced empathy before and after the conversations, respectively. To help minimize this gap, we develop a synthetic multi-turn conversational generation pipeline and steer responses toward our defined empathy patterns based on the context that more closely matches users' expectations. We then train empathetic expert adapters for context-specific empathy that specialize in varying empathy levels based on the recognized task. Our empirical results demonstrate a significant gap reduction of 72.66% between perceived and desired empathy with scores increasing by an average factor of 2.43 as measured by our metrics and reward models. Additionally, our trained empathetic expert adapters demonstrate superior effectiveness in preserving empathy patterns throughout conversation turns, outperforming system prompts, which tend to dramatically diminish in impact as conversations lengthen.
With the widespread application of Large Language Models (LLMs), their associated security issues have become increasingly prominent, severely constraining their trustworthy deployment in critical domains. This paper proposes a novel safety response framework designed to systematically safeguard LLMs at both the input and output levels. At the input level, the framework employs a supervised fine-tuning-based safety classification model. Through a fine-grained four-tier taxonomy (Safe, Unsafe, Conditionally Safe, Focused Attention), it performs precise risk identification and differentiated handling of user queries, significantly enhancing risk coverage and business scenario adaptability, and achieving a risk recall rate of 99.3%. At the output level, the framework integrates Retrieval-Augmented Generation (RAG) with a specifically fine-tuned interpretation model, ensuring all responses are grounded in a real-time, trustworthy knowledge base. This approach eliminates information fabrication and enables result traceability. Experimental results demonstrate that our proposed safety control model achieves a significantly higher safety score on public safety evaluation benchmarks compared to the baseline model, TinyR1-Safety-8B. Furthermore, on our proprietary high-risk test set, the framework's components attained a perfect 100% safety score, validating their exceptional protective capabilities in complex risk scenarios. This research provides an effective engineering pathway for building high-security, high-trust LLM applications.
Large language models enable flexible multi-agent planning but remain fragile in practice: verification is often circular, state changes are not tracked for repair, and small faults trigger costly global recomputation. We present ALAS, a stateful, disruption-aware framework that separates planning from non-circular validation, records a versioned execution log for grounded checks and restore points, and performs localized repair that preserves work in progress. The validator operates independently of the planning LLM with fresh, bounded context, avoiding self-check loops and mid-context attrition. The repair protocol edits only the minimal affected region under explicit policies (retry, catch, timeout, backoff, idempotency keys, compensation, loop guards) defined in a canonical workflow IR that maps to Amazon States Language and Argo Workflows. On job-shop scheduling suites (DMU, TA) across five classical benchmarks, ALAS matches or exceeds strong single-LLM and multi-agent baselines, achieving 83.7% success, reducing token usage by 60%, and running 1.82times faster under comparable settings. A minimal reliability study shows that the validator detects injected structural faults with low overhead, and that localized repair contains runtime perturbations with a bounded edit radius and less makespan degradation than global recompute. Results indicate that the combination of validator isolation, versioned execution logs, and localized repair provides measurable efficiency, feasibility, and scalability for multi-agent LLM planning. Code and seeds will be released.
The safe deployment of autonomous systems in safety-critical settings requires a paradigm that combines human expertise with AI-driven analysis, especially when anomalies are unforeseen. We introduce AURA (Autonomous Resilience Agent), a collaborative framework for anomaly and fault diagnostics in robotics. AURA integrates large language models (LLMs), a high-fidelity digital twin (DT), and human-in-the-loop interaction to detect and respond to anomalous behavior in real time. The architecture uses two agents with clear roles: (i) a low-level State Anomaly Characterization Agent that monitors telemetry and converts signals into a structured natural-language problem description, and (ii) a high-level Diagnostic Reasoning Agent that conducts a knowledge-grounded dialogue with an operator to identify root causes, drawing on external sources. Human-validated diagnoses are then converted into new training examples that refine the low-level perceptual model. This feedback loop progressively distills expert knowledge into the AI, transforming it from a static tool into an adaptive partner. We describe the framework's operating principles and provide a concrete implementation, establishing a pattern for trustworthy, continually improving human-robot teams.
Evaluating large language models (LLMs) as judges is increasingly critical for building scalable and trustworthy evaluation pipelines. We present ScalingEval, a large-scale benchmarking study that systematically compares 36 LLMs, including GPT, Gemini, Claude, and Llama, across multiple product categories using a consensus-driven evaluation protocol. Our multi-agent framework aggregates pattern audits and issue codes into ground-truth labels via scalable majority voting, enabling reproducible comparison of LLM evaluators without human annotation. Applied to large-scale complementary-item recommendation, the benchmark reports four key findings: (i) Anthropic Claude 3.5 Sonnet achieves the highest decision confidence; (ii) Gemini 1.5 Pro offers the best overall performance across categories; (iii) GPT-4o provides the most favorable latency-accuracy-cost tradeoff; and (iv) GPT-OSS 20B leads among open-source models. Category-level analysis shows strong consensus in structured domains (Electronics, Sports) but persistent disagreement in lifestyle categories (Clothing, Food). These results establish ScalingEval as a reproducible benchmark and evaluation protocol for LLMs as judges, with actionable guidance on scaling, reliability, and model family tradeoffs.
Large language models (LLMs) have seen increasing popularity in enterprise applications where AI agents and humans engage in objective-driven interactions. However, these systems are difficult to evaluate: data may be complex and unlabeled; human annotation is often impractical at scale; custom metrics can monitor for specific errors, but not previously-undetected ones; and LLM judges can produce unreliable results. We introduce the first set of unsupervised metrics for objective-driven interactions, leveraging statistical properties of unlabeled interaction data and using fine-tuned LLMs to adapt to distributional shifts. We develop metrics for labeling user goals, measuring goal completion, and quantifying LLM uncertainty without grounding evaluations in human-generated ideal responses. Our approach is validated on open-domain and task-specific interaction data.
Open data repositories hold potential for evidence-based decision-making, yet are inaccessible to non-experts lacking expertise in dataset discovery, schema mapping, and statistical analysis. Large language models show promise for individual tasks, but end-to-end analytical workflows expose fundamental limitations: attention dilutes across growing contexts, specialized reasoning patterns interfere, and errors propagate undetected. We present PublicAgent, a multi-agent framework that addresses these limitations through decomposition into specialized agents for intent clarification, dataset discovery, analysis, and reporting. This architecture maintains focused attention within agent contexts and enables validation at each stage. Evaluation across five models and 50 queries derives five design principles for multi-agent LLM systems. First, specialization provides value independent of model strength--even the strongest model shows 97.5% agent win rates, with benefits orthogonal to model scale. Second, agents divide into universal (discovery, analysis) and conditional (report, intent) categories. Universal agents show consistent effectiveness (std dev 12.4%) while conditional agents vary by model (std dev 20.5%). Third, agents mitigate distinct failure modes--removing discovery or analysis causes catastrophic failures (243-280 instances), while removing report or intent causes quality degradation. Fourth, architectural benefits persist across task complexity with stable win rates (86-92% analysis, 84-94% discovery), indicating workflow management value rather than reasoning enhancement. Fifth, wide variance in agent effectiveness across models (42-96% for analysis) requires model-aware architecture design. These principles guide when and why specialization is necessary for complex analytical workflows while enabling broader access to public data through natural language interfaces.
Despite recent progress in using Large Language Models (LLMs) for automatically generating 3D scenes, generated scenes often lack realistic spatial layouts and object attributes found in real-world environments. As this problem stems from insufficiently detailed, coarse-grained instructions, advancing 3D scene synthesis guided by more detailed, fine-grained instructions that reflect real-world environments becomes crucial. Without such realistic scenes, training embodied agents in unrealistic environments can lead them to learn priors that diverge significantly from real-world physics and semantics, degrading their performance when deployed. Thus, verifying the alignment between the fine-grained instruction and the generated scene is essential for effective learning. However, current evaluation methods, such as CLIPScore and vision-language models (VLMs), often fail to reliably assess such alignment. This shortcoming arises primarily from their shallow understanding of 3D scenes, which often leads to improperly grounded scene components. To address this, we introduce LEGO-Eval, an evaluation framework equipped with diverse tools designed to explicitly ground scene components, enabling more accurate alignment assessments. We also present LEGO-Bench, a benchmark of detailed instructions that specify complex layouts and attributes of real-world environments. Experiments demonstrate that LEGO-Eval outperforms VLM-as-a-judge by 0.41 F1 score in assessing scene-instruction alignment. Benchmarking with LEGO-Bench reveals significant limitations in current generation methods. Across all evaluated approaches, success rates reached at most 10% in generating scenes that fully align with fine-grained instructions.
Recent advances in Large Language Model (LLM)-based agents have been propelled by Retrieval-Augmented Generation (RAG), which grants the models access to vast external knowledge bases. Despite RAG's success in improving agent performance, agent-level cache management, particularly constructing, maintaining, and updating a compact, relevant corpus dynamically tailored to each agent's need, remains underexplored. Therefore, we introduce ARC (Agent RAG Cache Mechanism), a novel, annotation-free caching framework that dynamically manages small, high-value corpora for each agent. By synthesizing historical query distribution patterns with the intrinsic geometry of cached items in the embedding space, ARC automatically maintains a high-relevance cache. With comprehensive experiments on three retrieval datasets, our experimental results demonstrate that ARC reduces storage requirements to 0.015% of the original corpus while offering up to 79.8% has-answer rate and reducing average retrieval latency by 80%. Our results demonstrate that ARC can drastically enhance efficiency and effectiveness in RAG-powered LLM agents.
Typical search agents concatenate the entire interaction history into the LLM context, preserving information integrity but producing long, noisy contexts, resulting in high computation and memory costs. In contrast, using only the current turn avoids this overhead but discards essential information. This trade-off limits the scalability of search agents. To address this challenge, we propose MemSearcher, an agent workflow that iteratively maintains a compact memory and combines the current turn with it. At each turn, MemSearcher fuses the user's question with the memory to generate reasoning traces, perform search actions, and update memory to retain only information essential for solving the task. This design stabilizes context length across multi-turn interactions, improving efficiency without sacrificing accuracy. To optimize this workflow, we introduce multi-context GRPO, an end-to-end RL framework that jointly optimize reasoning, search strategies, and memory management of MemSearcher Agents. Specifically, multi-context GRPO samples groups of trajectories under different contexts and propagates trajectory-level advantages across all conversations within them. Trained on the same dataset as Search-R1, MemSearcher achieves significant improvements over strong baselines on seven public benchmarks: +11% on Qwen2.5-3B-Instruct and +12% on Qwen2.5-7B-Instruct relative average gains. Notably, the 3B-based MemSearcher even outperforms 7B-based baselines, demonstrating that striking a balance between information integrity and efficiency yields both higher accuracy and lower computational overhead. The code and models will be publicly available at https://github.com/icip-cas/MemSearcher
Large language models (LLMs) exhibit complementary strengths across domains and come with varying inference costs, motivating the design of multi-agent LLM systems where specialized models collaborate efficiently. Existing approaches predominantly rely on decentralized frameworks, which invoke multiple LLMs for every input and thus lead to substantial and uncontrolled inference costs. In this work, we introduce a centralized multi-LLM framework, where a controller LLM selectively coordinates a pool of expert models in a cost-efficient and cost-controllable manner. We formulate this coordination problem as reinforcement learning with dual objectives: maximizing task performance while minimizing the overall inference cost. In addition, we expect the multi-agent system to have adapted behavior with different budget conditions during inference. To this end, we propose CoRL, a reinforcement learning framework that optimizes the performance cost trade-off in a controllable multi-budget setting. Experiments on four diverse benchmarks demonstrate that CoRL enables a single system to surpass the best expert LLM under high-budget settings, while maintaining strong performance in more economical low-budget modes, highlighting the effectiveness of centralized coordination for scalable and cost-efficient multi-agent LLM systems.
We argue that sixth-generation (6G) intelligence is not fluent token prediction but the capacity to imagine and choose -- to simulate future scenarios, weigh trade-offs, and act with calibrated uncertainty. We reframe open radio access network (O-RAN) near-real-time (Near-RT) control via counterfactual dynamics and a world modeling (WM) paradigm that learns an action-conditioned generative state space. This enables quantitative "what-if" forecasting beyond large language models (LLMs) as the primary modeling primitive. Actions such as physical resource blocks (PRBs) are treated as first-class control inputs in a causal world model, and both aleatoric and epistemic uncertainty are modeled for prediction and what-if analysis. An agentic, model predictive control (MPC)-based cross-entropy method (CEM) planner operates over short horizons, using prior-mean rollouts within data-driven PRB bounds to maximize a deterministic reward. The model couples multi-scale structured state-space mixtures (MS3M) with a compact stochastic latent to form WM-MS3M, summarizing key performance indicators (KPIs) histories and predicting next-step KPIs under hypothetical PRB sequences. On realistic O-RAN traces, WM-MS3M cuts mean absolute error (MAE) by 1.69% versus MS3M with 32% fewer parameters and similar latency, and achieves 35-80% lower root mean squared error (RMSE) than attention/hybrid baselines with 2.3-4.1x faster inference, enabling rare-event simulation and offline policy screening.
Current evaluations of Large Language Model (LLM) agents primarily emphasize task completion, often overlooking resource efficiency and adaptability. This neglects a crucial capability: agents' ability to devise and adjust cost-optimal plans in response to changing environments. To bridge this gap, we introduce CostBench, a scalable, cost-centric benchmark designed to evaluate agents' economic reasoning and replanning abilities. Situated in the travel-planning domain, CostBench comprises tasks solvable via multiple sequences of atomic and composite tools with diverse, customizable costs. It also supports four types of dynamic blocking events, such as tool failures and cost changes, to simulate real-world unpredictability and necessitate agents to adapt in real time. Evaluating leading open-sourced and proprietary models on CostBench reveals a substantial gap in cost-aware planning: agents frequently fail to identify cost-optimal solutions in static settings, with even GPT-5 achieving less than 75% exact match rate on the hardest tasks, and performance further dropping by around 40% under dynamic conditions. By diagnosing these weaknesses, CostBench lays the groundwork for developing future agents that are both economically rational and robust.