Cooperative multi-agent planning requires agents to make joint decisions with partial information and limited communication. Coordination at the trajectory level often fails, as small deviations in timing or movement cascade into conflicts. Symbolic planning mitigates this challenge by raising the level of abstraction and providing a minimal vocabulary of actions that enable synchronization and collective progress. We present DR. WELL, a decentralized neurosymbolic framework for cooperative multi-agent planning. Cooperation unfolds through a two-phase negotiation protocol: agents first propose candidate roles with reasoning and then commit to a joint allocation under consensus and environment constraints. After commitment, each agent independently generates and executes a symbolic plan for its role without revealing detailed trajectories. Plans are grounded in execution outcomes via a shared world model that encodes the current state and is updated as agents act. By reasoning over symbolic plans rather than raw trajectories, DR. WELL avoids brittle step-level alignment and enables higher-level operations that are reusable, synchronizable, and interpretable. Experiments on cooperative block-push tasks show that agents adapt across episodes, with the dynamic world model capturing reusable patterns and improving task completion rates and efficiency. Experiments on cooperative block-push tasks show that our dynamic world model improves task completion and efficiency through negotiation and self-refinement, trading a time overhead for evolving, more efficient collaboration strategies.
Retrieval-Augmented Generation (RAG) is a critical technique for grounding Large Language Models (LLMs) in factual evidence, yet evaluating RAG systems in specialized, safety-critical domains remains a significant challenge. Existing evaluation frameworks often rely on heuristic-based metrics that fail to capture domain-specific nuances and other works utilize LLM-as-a-Judge approaches that lack validated alignment with human judgment. This paper introduces RAGalyst, an automated, human-aligned agentic framework designed for the rigorous evaluation of domain-specific RAG systems. RAGalyst features an agentic pipeline that generates high-quality, synthetic question-answering (QA) datasets from source documents, incorporating an agentic filtering step to ensure data fidelity. The framework refines two key LLM-as-a-Judge metrics-Answer Correctness and Answerability-using prompt optimization to achieve a strong correlation with human annotations. Applying this framework to evaluate various RAG components across three distinct domains (military operations, cybersecurity, and bridge engineering), we find that performance is highly context-dependent. No single embedding model, LLM, or hyperparameter configuration proves universally optimal. Additionally, we provide an analysis on the most common low Answer Correctness reasons in RAG. These findings highlight the necessity of a systematic evaluation framework like RAGalyst, which empowers practitioners to uncover domain-specific trade-offs and make informed design choices for building reliable and effective RAG systems. RAGalyst is available on our Github.
Web agents, like OpenAI's Operator and Google's Project Mariner, are powerful agentic systems pushing the boundaries of Large Language Models (LLM). They can autonomously interact with the internet at the user's behest, such as navigating websites, filling search masks, and comparing price lists. Though web agent research is thriving, induced sustainability issues remain largely unexplored. To highlight the urgency of this issue, we provide an initial exploration of the energy and $CO_2$ cost associated with web agents from both a theoretical -via estimation- and an empirical perspective -by benchmarking. Our results show how different philosophies in web agent creation can severely impact the associated expended energy, and that more energy consumed does not necessarily equate to better results. We highlight a lack of transparency regarding disclosing model parameters and processes used for some web agents as a limiting factor when estimating energy consumption. Our work contributes towards a change in thinking of how we evaluate web agents, advocating for dedicated metrics measuring energy consumption in benchmarks.
Traditional vehicle routing systems efficiently optimize singular metrics like time or distance, and when considering multiple metrics, they need more processes to optimize . However, they lack the capability to interpret and integrate the complex, semantic, and dynamic contexts of human drivers, such as multi-step tasks, situational constraints, or urgent needs. This paper introduces and evaluates PAVe (Personalized Agentic Vehicular Routing), a hybrid agentic assistant designed to augment classical pathfinding algorithms with contextual reasoning. Our approach employs a Large Language Model (LLM) agent that operates on a candidate set of routes generated by a multi-objective (time, CO2) Dijkstra algorithm. The agent evaluates these options against user-provided tasks, preferences, and avoidance rules by leveraging a pre-processed geospatial cache of urban Points of Interest (POIs). In a benchmark of realistic urban scenarios, PAVe successfully used complex user intent into appropriate route modifications, achieving over 88% accuracy in its initial route selections with a local model. We conclude that combining classical routing algorithms with an LLM-based semantic reasoning layer is a robust and effective approach for creating personalized, adaptive, and scalable solutions for urban mobility optimization.
Large language models (LLMs) have demonstrated the promise to revolutionize the field of software engineering. Among other things, LLM agents are rapidly gaining momentum in their application to software development, with practitioners claiming a multifold productivity increase after adoption. Yet, empirical evidence is lacking around these claims. In this paper, we estimate the causal effect of adopting a widely popular LLM agent assistant, namely Cursor, on development velocity and software quality. The estimation is enabled by a state-of-the-art difference-in-differences design comparing Cursor-adopting GitHub projects with a matched control group of similar GitHub projects that do not use Cursor. We find that the adoption of Cursor leads to a significant, large, but transient increase in project-level development velocity, along with a significant and persistent increase in static analysis warnings and code complexity. Further panel generalized method of moments estimation reveals that the increase in static analysis warnings and code complexity acts as a major factor causing long-term velocity slowdown. Our study carries implications for software engineering practitioners, LLM agent assistant designers, and researchers.
Large language models (LLMs) are increasingly deployed as "agents" for decision-making (DM) in interactive and dynamic environments. Yet, since they were not originally designed for DM, recent studies show that LLMs can struggle even in basic online DM problems, failing to achieve low regret or an effective exploration-exploitation tradeoff. To address this, we introduce Iterative Regret-Minimization Fine-Tuning (Iterative RMFT), a post-training procedure that repeatedly distills low-regret decision trajectories back into the base model. At each iteration, the model rolls out multiple decision trajectories, selects the k-lowest regret ones, and fine-tunes itself on them. Unlike prior methods that (a) distill action sequences from known DM algorithms or (b) rely on manually crafted chain-of-thought templates, our approach leverages the regret metric to elicit the model's own DM ability and reasoning rationales. This reliance on model-generated reasoning avoids rigid output engineering and provides more flexible, natural-language training signals. Empirical results show that Iterative RMFT improves LLMs' DM performance across diverse models - from Transformers with numerical input/output, to open-weight LLMs, and advanced closed-weight models like GPT-4o mini. Its flexibility in output and reasoning formats enables generalization across tasks with varying horizons, action spaces, reward processes, and natural-language contexts. Finally, we provide theoretical insight showing that a single-layer Transformer under this paradigm can act as a no-regret learner in a simplified setting. Overall, Iterative RMFT offers a principled and general post-training framework for enhancing LLMs' decision-making capabilities.
We introduce GUI-360$^\circ$, a large-scale, comprehensive dataset and benchmark suite designed to advance computer-using agents (CUAs). CUAs present unique challenges and is constrained by three persistent gaps: a scarcity of real-world CUA tasks, the lack of automated collection-and-annotation pipelines for multi-modal trajectories, and the absence of a unified benchmark that jointly evaluates GUI grounding, screen parsing, and action prediction. GUI-360$^\circ$ addresses these gaps with an LLM-augmented, largely automated pipeline for query sourcing, environment-template construction, task instantiation, batched execution, and LLM-driven quality filtering. The released corpus contains over 1.2M executed action steps across thousands of trajectories in popular Windows office applications, and includes full-resolution screenshots, accessibility metadata when available, instantiated goals, intermediate reasoning traces, and both successful and failed action trajectories. The dataset supports three canonical tasks, GUI grounding, screen parsing, and action prediction, and a hybrid GUI+API action space that reflects modern agent designs. Benchmarking state-of-the-art vision--language models on GUI-360$^\circ$ reveals substantial out-of-the-box shortcomings in grounding and action prediction; supervised fine-tuning and reinforcement learning yield significant gains but do not close the gap to human-level reliability. We release GUI-360$^\circ$ and accompanying code to facilitate reproducible research and accelerate progress on robust desktop CUAs. The full dataset has been made public on https://huggingface.co/datasets/vyokky/GUI-360.
The proliferation of AI-generated content has created an absurd communication theater where senders use LLMs to inflate simple ideas into verbose content, recipients use LLMs to compress them back into summaries, and as a consequence neither party engage with authentic content. LAAC (LLM as a Communicator) proposes a paradigm shift - positioning LLMs as intelligent communication intermediaries that capture the sender's intent through structured dialogue and facilitate genuine knowledge exchange with recipients. Rather than perpetuating cycles of AI-generated inflation and compression, LAAC enables authentic communication across diverse contexts including academic papers, proposals, professional emails, and cross-platform content generation. However, deploying LLMs as trusted communication intermediaries raises critical questions about information fidelity, consistency, and reliability. This position paper systematically evaluates the trustworthiness requirements for LAAC's deployment across multiple communication domains. We investigate three fundamental dimensions: (1) Information Capture Fidelity - accuracy of intent extraction during sender interviews across different communication types, (2) Reproducibility - consistency of structured knowledge across multiple interaction instances, and (3) Query Response Integrity - reliability of recipient-facing responses without hallucination, source conflation, or fabrication. Through controlled experiments spanning multiple LAAC use cases, we assess these trust dimensions using LAAC's multi-agent architecture. Preliminary findings reveal measurable trust gaps that must be addressed before LAAC can be reliably deployed in high-stakes communication scenarios.
Text-to-SQL systems provide a natural language interface that can enable even laymen to access information stored in databases. However, existing Large Language Models (LLM) struggle with SQL generation from natural instructions due to large schema sizes and complex reasoning. Prior work often focuses on complex, somewhat impractical pipelines using flagship models, while smaller, efficient models remain overlooked. In this work, we explore three multi-agent LLM pipelines, with systematic performance benchmarking across a range of small to large open-source models: (1) Multi-agent discussion pipeline, where agents iteratively critique and refine SQL queries, and a judge synthesizes the final answer; (2) Planner-Coder pipeline, where a thinking model planner generates stepwise SQL generation plans and a coder synthesizes queries; and (3) Coder-Aggregator pipeline, where multiple coders independently generate SQL queries, and a reasoning agent selects the best query. Experiments on the Bird-Bench Mini-Dev set reveal that Multi-Agent discussion can improve small model performance, with up to 10.6% increase in Execution Accuracy for Qwen2.5-7b-Instruct seen after three rounds of discussion. Among the pipelines, the LLM Reasoner-Coder pipeline yields the best results, with DeepSeek-R1-32B and QwQ-32B planners boosting Gemma 3 27B IT accuracy from 52.4% to the highest score of 56.4%. Codes are available at https://github.com/treeDweller98/bappa-sql.
Redistricting plays a central role in shaping how votes are translated into political power. While existing computational methods primarily aim to generate large ensembles of legally valid districting plans, they often neglect the strategic dynamics involved in the selection process. This oversight creates opportunities for partisan actors to cherry-pick maps that, while technically compliant, are politically advantageous. Simply satisfying formal constraints does not ensure fairness when the selection process itself can be manipulated. We propose \textbf{Agentmandering}, a framework that reimagines redistricting as a turn-based negotiation between two agents representing opposing political interests. Drawing inspiration from game-theoretic ideas, particularly the \textit{Choose-and-Freeze} protocol, our method embeds strategic interaction into the redistricting process via large language model (LLM) agents. Agents alternate between selecting and freezing districts from a small set of candidate maps, gradually partitioning the state through constrained and interpretable choices. Evaluation on post-2020 U.S. Census data across all states shows that Agentmandering significantly reduces partisan bias and unfairness, while achieving 2 to 3 orders of magnitude lower variance than standard baselines. These results demonstrate both fairness and stability, especially in swing-state scenarios. Our code is available at https://github.com/Lihaogx/AgentMandering.
The development of LLM-based autonomous agents for end-to-end software development represents a significant paradigm shift in software engineering. However, the scientific evaluation of these systems is hampered by significant challenges, including overly simplistic benchmarks and the difficulty of conducting fair comparisons between different agent architectures due to confounding implementation variables. To address these limitations, we first construct a challenging and dynamically curated E2EDevBench to simulate realistic development scenarios. Second, we propose a hybrid evaluation framework that combines test-case-based functional assessment with fine-grained, LLM-based requirement verification. Using this framework, we conduct a controlled empirical study on three representative agent architectures implemented upon a unified foundation to isolate the impact of workflow design. Our findings reveal that state-of-the-art agents can fulfill approximately 50\% of requirements on \bench{}, but their success is critically dependent on the architectural strategy for task decomposition and collaboration. Furthermore, our analysis indicates that the primary bottleneck is the omission of requirements and inadequate self-verification. This work provides the community with a more realistic benchmark, a comprehensive evaluation framework, and crucial insights into the current capabilities and core challenges of software development agents, guiding future research toward enhancing requirement comprehension and planning.
Multi-Agentic AI systems, powered by large language models (LLMs), are inherently non-deterministic and prone to silent failures such as drift, cycles, and missing details in outputs, which are difficult to detect. We introduce the task of anomaly detection in agentic trajectories to identify these failures and present a dataset curation pipeline that captures user behavior, agent non-determinism, and LLM variation. Using this pipeline, we curate and label two benchmark datasets comprising \textbf{4,275 and 894} trajectories from Multi-Agentic AI systems. Benchmarking anomaly detection methods on these datasets, we show that supervised (XGBoost) and semi-supervised (SVDD) approaches perform comparably, achieving accuracies up to 98% and 96%, respectively. This work provides the first systematic study of anomaly detection in Multi-Agentic AI systems, offering datasets, benchmarks, and insights to guide future research.
Recent LLM-based agents have demonstrated strong capabilities in automated ML engineering. However, they heavily rely on repeated full training runs to evaluate candidate solutions, resulting in significant computational overhead, limited scalability to large search spaces, and slow iteration cycles. To address these challenges, we introduce ArchPilot, a multi-agent system that integrates architecture generation, proxy-based evaluation, and adaptive search into a unified framework. ArchPilot consists of three specialized agents: an orchestration agent that coordinates the search process using a Monte Carlo Tree Search (MCTS)-inspired novel algorithm with a restart mechanism and manages memory of previous candidates; a generation agent that iteratively generates, improves, and debugs candidate architectures; and an evaluation agent that executes proxy training runs, generates and optimizes proxy functions, and aggregates the proxy scores into a fidelity-aware performance metric. This multi-agent collaboration allows ArchPilot to prioritize high-potential candidates with minimal reliance on expensive full training runs, facilitating efficient ML engineering under limited budgets. Experiments on MLE-Bench demonstrate that ArchPilot outperforms SOTA baselines such as AIDE and ML-Master, validating the effectiveness of our multi-agent system.
In multi-agent settings, such as debate, reflection, or tool-calling, large language models (LLMs) pass messages as plain tokens, discarding most latent semantics. This constrains information transfer and adds unnecessary computational overhead. We form a latent bridge via vector translations, which use learned mappings that enable direct semantic exchange between representation spaces. A dual-encoder translator trained between Llama-2-7B and Mistral-7B-Instruct attains an average cosine alignment of 0.538. Injecting the translated vectors at 30 percent blending strength steers the target model's generation without destabilizing logits. Bidirectional evaluation shows a 2.01:1 transfer asymmetry, indicating that general-purpose models yield more transferable representations than instruction-tuned variants. This conservative injection preserves computational stability while demonstrating that cross-model latent communication is feasible, enabling collaborative AI systems that share meaning rather than tokens.
We present an agentic flow consisting of multiple agents that combine specialized LLMs and hardware simulation tools to collaboratively complete the complex task of Register Transfer Level (RTL) generation without human intervention. A key feature of the proposed flow is the progressive error feedback system of agents (PEFA), a self-correcting mechanism that leverages iterative error feedback to progressively increase the complexity of the approach. The generated RTL includes checks for compilation, functional correctness, and synthesizable constructs. To validate this adaptive approach to code generation, benchmarking is performed using two opensource natural language-to-RTL datasets. We demonstrate the benefits of the proposed approach implemented on an open source agentic framework, using both open- and closed-source LLMs, effectively bridging the performance gap between them. Compared to previously published methods, our approach sets a new benchmark, providing state-of-the-art pass rates while being efficient in token counts.
Automated Program Repair (APR) has advanced rapidly with Large Language Models (LLMs), but most existing methods remain computationally expensive, and focused on a small set of languages. Ruby, despite its widespread use in web development and the persistent challenges faced by its developers, has received little attention in APR research. In this paper, we introduce RAMP, a novel lightweight framework that formulates program repair as a feedback-driven, iterative process for Ruby. RAMP employs a team of collaborative agents that generate targeted tests, reflect on errors, and refine candidate fixes until a correct solution is found. Unlike prior approaches, RAMP is designed to avoid reliance on large multilingual repair databases or costly fine-tuning, instead operating directly on Ruby through lightweight prompting and test-driven feedback. Evaluation on the XCodeEval benchmark shows that RAMP achieves a pass@1 of 67% on Ruby, outper-forming prior approaches. RAMP converges quickly within five iterations, and ablation studies confirm that test generation and self-reflection are key drivers of its performance. Further analysis shows that RAMP is particularly effective at repairing wrong answers, compilation errors, and runtime errors. Our approach provides new insights into multi-agent repair strategies, and establishes a foundation for extending LLM-based debugging tools to under-studied languages.
We develop KnowThyself, an agentic assistant that advances large language model (LLM) interpretability. Existing tools provide useful insights but remain fragmented and code-intensive. KnowThyself consolidates these capabilities into a chat-based interface, where users can upload models, pose natural language questions, and obtain interactive visualizations with guided explanations. At its core, an orchestrator LLM first reformulates user queries, an agent router further directs them to specialized modules, and the outputs are finally contextualized into coherent explanations. This design lowers technical barriers and provides an extensible platform for LLM inspection. By embedding the whole process into a conversational workflow, KnowThyself offers a robust foundation for accessible LLM interpretability.
Geothermal field development typically involves complex processes that require multi-disciplinary expertise in each process. Thus, decision-making often demands the integration of geological, geophysical, reservoir engineering, and operational data under tight time constraints. We present Geothermal Analytics and Intelligent Agent, or GAIA, an AI-based system for automation and assistance in geothermal field development. GAIA consists of three core components: GAIA Agent, GAIA Chat, and GAIA Digital Twin, or DT, which together constitute an agentic retrieval-augmented generation (RAG) workflow. Specifically, GAIA Agent, powered by a pre-trained large language model (LLM), designs and manages task pipelines by autonomously querying knowledge bases and orchestrating multi-step analyses. GAIA DT encapsulates classical and surrogate physics models, which, combined with built-in domain-specific subroutines and visualization tools, enable predictive modeling of geothermal systems. Lastly, GAIA Chat serves as a web-based interface for users, featuring a ChatGPT-like layout with additional functionalities such as interactive visualizations, parameter controls, and in-context document retrieval. To ensure GAIA's specialized capability for handling complex geothermal-related tasks, we curate a benchmark test set comprising various geothermal-related use cases, and we rigorously and continuously evaluate the system's performance. We envision GAIA as a pioneering step toward intelligent geothermal field development, capable of assisting human experts in decision-making, accelerating project workflows, and ultimately enabling automation of the development process.
Multimodal Large Language Models (MLLMs) are reshaping how modern agentic systems reason over sequential user-behavior data. However, whether textual or image representations of user behavior data are more effective for maximizing MLLM performance remains underexplored. We present \texttt{BehaviorLens}, a systematic benchmarking framework for assessing modality trade-offs in user-behavior reasoning across six MLLMs by representing transaction data as (1) a text paragraph, (2) a scatter plot, and (3) a flowchart. Using a real-world purchase-sequence dataset, we find that when data is represented as images, MLLMs next-purchase prediction accuracy is improved by 87.5% compared with an equivalent textual representation without any additional computational cost.
Optimizing large-language model (LLM) training on distributed domain-specific accelerator systems presents significant challenges due to its complex optimization space. Existing optimization methods, however, rely on time-consuming manual tuning or resource-intensive black-box searches, which struggle to keep pace with the rapidly evolving LLM domain, leading to slow development and underutilized resources. To address this, we introduce ASAP, an Agentic Solution to Auto-optimize Performance of Large-Scale LLM Training. It is a multi-agent system, featuring Coordinator, Analyzer, and Proposal agents, which integrates LLM reasoning with insights from performance profiling tools, roofline analysis, and a knowledge base of best practices and successful past optimizations from human experts. Our proposed design can automate the diagnosis of performance bottlenecks and recommend optimized sharding configurations with reasoning, thus effectively improving the efficiency of distributed LLM training. Experiments have shown that the ASAP-generated sharding configurations can contribute up to 28% training step time reduction and 1.43 times throughput improvement. When combined with additional optimization from human experts, throughput can be further increased to 2.58 times. The proposed ASAP promises to provide a scalable and explainable methodology for AI-assisted performance engineering in large-scale LLM training.
While reinforcement learning (RL) can empower large language model (LLM) agents by enabling self-improvement through interaction, its practical adoption remains challenging due to costly rollouts, limited task diversity, unreliable reward signals, and infrastructure complexity, all of which obstruct the collection of scalable experience data. To address these challenges, we introduce DreamGym, the first unified framework designed to synthesize diverse experiences with scalability in mind to enable effective online RL training for autonomous agents. Rather than relying on expensive real-environment rollouts, DreamGym distills environment dynamics into a reasoning-based experience model that derives consistent state transitions and feedback signals through step-by-step reasoning, enabling scalable agent rollout collection for RL. To improve the stability and quality of transitions, DreamGym leverages an experience replay buffer initialized with offline real-world data and continuously enriched with fresh interactions to actively support agent training. To improve knowledge acquisition, DreamGym adaptively generates new tasks that challenge the current agent policy, enabling more effective online curriculum learning. Experiments across diverse environments and agent backbones demonstrate that DreamGym substantially improves RL training, both in fully synthetic settings and in sim-to-real transfer scenarios. On non-RL-ready tasks like WebArena, DreamGym outperforms all baselines by over 30%. And in RL-ready but costly settings, it matches GRPO and PPO performance using only synthetic interactions. When transferring a policy trained purely on synthetic experiences to real-environment RL, DreamGym yields significant additional performance gains while requiring far fewer real-world interactions, providing a scalable warm-start strategy for general-purpose RL.
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.