Recent research has been increasingly focusing on developing 3D world models that simulate complex real-world scenarios. World models have found broad applications across various domains, including embodied AI, autonomous driving, entertainment, etc. A more realistic simulation with accurate physics will effectively narrow the sim-to-real gap and allow us to gather rich information about the real world conveniently. While traditional manual modeling has enabled the creation of virtual 3D scenes, modern approaches have leveraged advanced machine learning algorithms for 3D world generation, with most recent advances focusing on generative methods that can create virtual worlds based on user instructions. This work explores such a research direction by proposing LatticeWorld, a simple yet effective 3D world generation framework that streamlines the industrial production pipeline of 3D environments. LatticeWorld leverages lightweight LLMs (LLaMA-2-7B) alongside the industry-grade rendering engine (e.g., Unreal Engine 5) to generate a dynamic environment. Our proposed framework accepts textual descriptions and visual instructions as multimodal inputs and creates large-scale 3D interactive worlds with dynamic agents, featuring competitive multi-agent interaction, high-fidelity physics simulation, and real-time rendering. We conduct comprehensive experiments to evaluate LatticeWorld, showing that it achieves superior accuracy in scene layout generation and visual fidelity. Moreover, LatticeWorld achieves over a $90\times$ increase in industrial production efficiency while maintaining high creative quality compared with traditional manual production methods. Our demo video is available at https://youtu.be/8VWZXpERR18
Large Language Models (LLMs) are increasingly being deployed in high-risk domains where opacity, bias, and instability undermine trust and accountability. Traditional explainability methods, focused on surface outputs, do not capture the reasoning pathways, planning logic, and systemic impacts of agentic LLMs. We introduce TAXAL (Triadic Alignment for eXplainability in Agentic LLMs), a triadic fusion framework that unites three complementary dimensions: cognitive (user understanding), functional (practical utility), and causal (faithful reasoning). TAXAL provides a unified, role-sensitive foundation for designing, evaluating, and deploying explanations in diverse sociotechnical settings. Our analysis synthesizes existing methods, ranging from post-hoc attribution and dialogic interfaces to explanation-aware prompting, and situates them within the TAXAL triadic fusion model. We further demonstrate its applicability through case studies in law, education, healthcare, and public services, showing how explanation strategies adapt to institutional constraints and stakeholder roles. By combining conceptual clarity with design patterns and deployment pathways, TAXAL advances explainability as a technical and sociotechnical practice, supporting trustworthy and context-sensitive LLM applications in the era of agentic AI.
Automated web testing plays a critical role in ensuring high-quality user experiences and delivering business value. Traditional approaches primarily focus on code coverage and load testing, but often fall short of capturing complex user behaviors, leaving many usability issues undetected. The emergence of large language models (LLM) and AI agents opens new possibilities for web testing by enabling human-like interaction with websites and a general awareness of common usability problems. In this work, we present WebProber, a prototype AI agent-based web testing framework. Given a URL, WebProber autonomously explores the website, simulating real user interactions, identifying bugs and usability issues, and producing a human-readable report. We evaluate WebProber through a case study of 120 academic personal websites, where it uncovered 29 usability issues--many of which were missed by traditional tools. Our findings highlight agent-based testing as a promising direction while outlining directions for developing next-generation, user-centered testing frameworks.
Shared autonomy is a promising paradigm in robotic systems, particularly within the maritime domain, where complex, high-risk, and uncertain environments necessitate effective human-robot collaboration. This paper investigates the interaction of three complementary approaches to advance shared autonomy in heterogeneous marine robotic fleets: (i) the integration of Large Language Models (LLMs) to facilitate intuitive high-level task specification and support hull inspection missions, (ii) the implementation of human-in-the-loop interaction frameworks in multi-agent settings to enable adaptive and intent-aware coordination, and (iii) the development of a modular Mission Manager based on Behavior Trees to provide interpretable and flexible mission control. Preliminary results from simulation and real-world lake-like environments demonstrate the potential of this multi-layered architecture to reduce operator cognitive load, enhance transparency, and improve adaptive behaviour alignment with human intent. Ongoing work focuses on fully integrating these components, refining coordination mechanisms, and validating the system in operational port scenarios. This study contributes to establishing a modular and scalable foundation for trustworthy, human-collaborative autonomy in safety-critical maritime robotics applications.
The ubiquitous computing resources in 6G networks provide ideal environments for the fusion of large language models (LLMs) and intelligent services through the agent framework. With auxiliary modules and planning cores, LLM-enabled agents can autonomously plan and take actions to deal with diverse environment semantics and user intentions. However, the limited resources of individual network devices significantly hinder the efficient operation of LLM-enabled agents with complex tool calls, highlighting the urgent need for efficient multi-level device collaborations. To this end, the framework and method of the LLM-enabled multi-agent system with dual-loop terminal-edge collaborations are proposed in 6G networks. Firstly, the outer loop consists of the iterative collaborations between the global agent and multiple sub-agents deployed on edge servers and terminals, where the planning capability is enhanced through task decomposition and parallel sub-task distribution. Secondly, the inner loop utilizes sub-agents with dedicated roles to circularly reason, execute, and replan the sub-task, and the parallel tool calling generation with offloading strategies is incorporated to improve efficiency. The improved task planning capability and task execution efficiency are validated through the conducted case study in 6G-supported urban safety governance. Finally, the open challenges and future directions are thoroughly analyzed in 6G networks, accelerating the advent of the 6G era.
AI agents -- powered by reasoning-capable large language models (LLMs) and integrated with tools, data, and web search -- are poised to transform the internet into a \emph{Web of Agents}: a machine-native ecosystem where autonomous agents interact, collaborate, and execute tasks at scale. Realizing this vision requires \emph{Agent Ranking} -- selecting agents not only by declared capabilities but by proven, recent performance. Unlike Web~1.0's PageRank, a global, transparent network of agent interactions does not exist; usage signals are fragmented and private, making ranking infeasible without coordination. We propose \textbf{DOVIS}, a five-layer operational protocol (\emph{Discovery, Orchestration, Verification, Incentives, Semantics}) that enables the collection of minimal, privacy-preserving aggregates of usage and performance across the ecosystem. On this substrate, we implement \textbf{AgentRank-UC}, a dynamic, trust-aware algorithm that combines \emph{usage} (selection frequency) and \emph{competence} (outcome quality, cost, safety, latency) into a unified ranking. We present simulation results and theoretical guarantees on convergence, robustness, and Sybil resistance, demonstrating the viability of coordinated protocols and performance-aware ranking in enabling a scalable, trustworthy Agentic Web.
The controllability of Large Language Models (LLMs) when used as conversational agents is a key challenge, particularly to ensure predictable and user-personalized responses. This work proposes an ontology-based approach to formally define conversational features that are typically qualitative in nature. By leveraging a set of linguistic descriptors, we derive quantitative definitions for qualitatively-defined concepts, enabling their integration into an ontology for reasoning and consistency checking. We apply this framework to the task of proficiency-level control in conversations, using CEFR language proficiency levels as a case study. These definitions are then formalized in description logic and incorporated into an ontology, which guides controlled text generation of an LLM through fine-tuning. Experimental results demonstrate that our approach provides consistent and explainable proficiency-level definitions, improving transparency in conversational AI.
This paper introduces OSC (Orchestrating Cognitive Synergy), a knowledge-aware adaptive collaboration framework designed to enhance cognitive synergy in multi-agent systems with large language models. While prior work has advanced agent selection and result aggregation, efficient linguistic interactions for deep collaboration among expert agents remain a critical bottleneck. OSC addresses this gap as a pivotal intermediate layer between selection and aggregation, introducing Collaborator Knowledge Models (CKM) to enable each agent to dynamically perceive its collaborators' cognitive states. Through real-time cognitive gap analysis, agents adaptively adjust communication behaviors, including content focus, detail level, and expression style, using learned strategies. Experiments on complex reasoning and problem-solving benchmarks demonstrate that OSC significantly improves task performance and communication efficiency, transforming "parallel-working individuals'' into a "deeply collaborative cognitive team.'' This framework not only optimizes multi-agent collaboration but also offers new insights into LLM agent interaction behaviors.
Modern Large Language Model (LLM) serving systems increasingly support interactive applications, like real-time chat assistants, code generation tools, and agentic workflows. However, the soaring energy cost of LLM inference presents a growing challenge for sustainable and cost-effective deployment. This paper introduces VoltanaLLM, a system for SLO-aware, energy-efficient LLM serving, built from a control theory perspective. VoltanaLLM co-designs frequency scaling and request routing in emerging prefill/decode disaggregated architectures, leveraging their decoupled execution to enable fine-grained phase-specific control. It consists of a feedback-driven frequency controller that dynamically adapts GPU frequency for prefill and decode phases, and a state-space router that explores routing decisions across frequency-scaled instances to minimize energy under latency constraints. We implement VoltanaLLM in SGLang and evaluate its performance over multiple state-of-the-art LLMs and real-world datasets. The results demonstrate that VoltanaLLM achieves up to 36.3% energy savings while maintaining near-perfect SLO attainment rate, paving the way for sustainable and intelligent LLM serving.
Retrieval-Augmented Generation (RAG) based on Large Language Models (LLMs) is a powerful solution to understand and query the industry's closed-source documents. However, basic RAG often struggles with complex QA tasks in legal and regulatory domains, particularly when dealing with numerous government documents. The top-$k$ strategy frequently misses golden chunks, leading to incomplete or inaccurate answers. To address these retrieval bottlenecks, we explore two strategies to improve evidence coverage and answer quality. The first is a One-SHOT retrieval method that adaptively selects chunks based on a token budget, allowing as much relevant content as possible to be included within the model's context window. Additionally, we design modules to further filter and refine the chunks. The second is an iterative retrieval strategy built on a Reasoning Agentic RAG framework, where a reasoning LLM dynamically issues search queries, evaluates retrieved results, and progressively refines the context over multiple turns. We identify query drift and retrieval laziness issues and further design two modules to tackle them. Through extensive experiments on a dataset of government documents, we aim to offer practical insights and guidance for real-world applications in legal and regulatory domains.
Explainable Reinforcement Learning (XRL) has emerged as a promising approach in improving the transparency of Reinforcement Learning (RL) agents. However, there remains a gap between complex RL policies and domain experts, due to the limited comprehensibility of XRL results and isolated coverage of current XRL approaches that leave users uncertain about which tools to employ. To address these challenges, we introduce TalkToAgent, a multi-agent Large Language Models (LLM) framework that delivers interactive, natural language explanations for RL policies. The architecture with five specialized LLM agents (Coordinator, Explainer, Coder, Evaluator, and Debugger) enables TalkToAgent to automatically map user queries to relevant XRL tools and clarify an agent's actions in terms of either key state variables, expected outcomes, or counterfactual explanations. Moreover, our approach extends previous counterfactual explanations by deriving alternative scenarios from qualitative behavioral descriptions, or even new rule-based policies. We validated TalkToAgent on quadruple-tank process control problem, a well-known nonlinear control benchmark. Results demonstrated that TalkToAgent successfully mapped user queries into XRL tasks with high accuracy, and coder-debugger interactions minimized failures in counterfactual generation. Furthermore, qualitative evaluation confirmed that TalkToAgent effectively interpreted agent's actions and contextualized their meaning within the problem domain.
As large language models transition to agentic systems, current safety evaluation frameworks face critical gaps in assessing deployment-specific risks. We introduce AgentSeer, an observability-based evaluation framework that decomposes agentic executions into granular action and component graphs, enabling systematic agentic-situational assessment. Through cross-model validation on GPT-OSS-20B and Gemini-2.0-flash using HarmBench single turn and iterative refinement attacks, we demonstrate fundamental differences between model-level and agentic-level vulnerability profiles. Model-level evaluation reveals baseline differences: GPT-OSS-20B (39.47% ASR) versus Gemini-2.0-flash (50.00% ASR), with both models showing susceptibility to social engineering while maintaining logic-based attack resistance. However, agentic-level assessment exposes agent-specific risks invisible to traditional evaluation. We discover "agentic-only" vulnerabilities that emerge exclusively in agentic contexts, with tool-calling showing 24-60% higher ASR across both models. Cross-model analysis reveals universal agentic patterns, agent transfer operations as highest-risk tools, semantic rather than syntactic vulnerability mechanisms, and context-dependent attack effectiveness, alongside model-specific security profiles in absolute ASR levels and optimal injection strategies. Direct attack transfer from model-level to agentic contexts shows degraded performance (GPT-OSS-20B: 57% human injection ASR; Gemini-2.0-flash: 28%), while context-aware iterative attacks successfully compromise objectives that failed at model-level, confirming systematic evaluation gaps. These findings establish the urgent need for agentic-situation evaluation paradigms, with AgentSeer providing the standardized methodology and empirical validation.
Personality manipulation in large language models (LLMs) is increasingly applied in customer service and agentic scenarios, yet its mechanisms and trade-offs remain unclear. We present a systematic study of personality control using the Big Five traits, comparing in-context learning (ICL), parameter-efficient fine-tuning (PEFT), and mechanistic steering (MS). Our contributions are fourfold. First, we construct a contrastive dataset with balanced high/low trait responses, enabling effective steering vector computation and fair cross-method evaluation. Second, we introduce a unified evaluation framework based on within-run $\Delta$ analysis that disentangles, reasoning capability, agent performance, and demographic bias across MMLU, GAIA, and BBQ benchmarks. Third, we develop trait purification techniques to separate openness from conscientiousness, addressing representational overlap in trait encoding. Fourth, we propose a three-level stability framework that quantifies method-, trait-, and combination-level robustness, offering practical guidance under deployment constraints. Experiments on Gemma-2-2B-IT and LLaMA-3-8B-Instruct reveal clear trade-offs: ICL achieves strong alignment with minimal capability loss, PEFT delivers the highest alignment at the cost of degraded task performance, and MS provides lightweight runtime control with competitive effectiveness. Trait-level analysis shows openness as uniquely challenging, agreeableness as most resistant to ICL, and personality encoding consolidating around intermediate layers. Taken together, these results establish personality manipulation as a multi-level probe into behavioral representation, linking surface conditioning, parameter encoding, and activation-level steering, and positioning mechanistic steering as a lightweight alternative to fine-tuning for both deployment and interpretability.
This paper introduces SePA (Search-enhanced Predictive AI Agent), a novel LLM health coaching system that integrates personalized machine learning and retrieval-augmented generation to deliver adaptive, evidence-based guidance. SePA combines: (1) Individualized models predicting daily stress, soreness, and injury risk from wearable sensor data (28 users, 1260 data points); and (2) A retrieval module that grounds LLM-generated feedback in expert-vetted web content to ensure contextual relevance and reliability. Our predictive models, evaluated with rolling-origin cross-validation and group k-fold cross-validation show that personalized models outperform generalized baselines. In a pilot expert study (n=4), SePA's retrieval-based advice was preferred over a non-retrieval baseline, yielding meaningful practical effect (Cliff's $\delta$=0.3, p=0.05). We also quantify latency performance trade-offs between response quality and speed, offering a transparent blueprint for next-generation, trustworthy personal health informatics systems.
Modeling & Simulation (M&S) approaches such as agent-based models hold significant potential to support decision-making activities in health, with recent examples including the adoption of vaccines, and a vast literature on healthy eating behaviors and physical activity behaviors. These models are potentially usable by different stakeholder groups, as they support policy-makers to estimate the consequences of potential interventions and they can guide individuals in making healthy choices in complex environments. However, this potential may not be fully realized because of the models' complexity, which makes them inaccessible to the stakeholders who could benefit the most. While Large Language Models (LLMs) can translate simulation outputs and the design of models into text, current approaches typically rely on one-size-fits-all summaries that fail to reflect the varied informational needs and stylistic preferences of clinicians, policymakers, patients, caregivers, and health advocates. This limitation stems from a fundamental gap: we lack a systematic understanding of what these stakeholders need from explanations and how to tailor them accordingly. To address this gap, we present a step-by-step framework to identify stakeholder needs and guide LLMs in generating tailored explanations of health simulations. Our procedure uses a mixed-methods design by first eliciting the explanation needs and stylistic preferences of diverse health stakeholders, then optimizing the ability of LLMs to generate tailored outputs (e.g., via controllable attribute tuning), and then evaluating through a comprehensive range of metrics to further improve the tailored generation of summaries.
Building reliable LLM agents requires decisions at two levels: the graph (which modules exist and how information flows) and the configuration of each node (models, prompts, tools, control knobs). Most existing optimizers tune configurations while holding the graph fixed, leaving structural failure modes unaddressed. We introduce Maestro, a framework-agnostic holistic optimizer for LLM agents that jointly searches over graphs and configurations to maximize agent quality, subject to explicit rollout/token budgets. Beyond numeric metrics, Maestro leverages reflective textual feedback from traces to prioritize edits, improving sample efficiency and targeting specific failure modes. On the IFBench and HotpotQA benchmarks, Maestro consistently surpasses leading prompt optimizers--MIPROv2, GEPA, and GEPA+Merge--by an average of 12%, 4.9%, and 4.86%, respectively; even when restricted to prompt-only optimization, it still leads by 9.65%, 2.37%, and 2.41%. Maestro achieves these results with far fewer rollouts than GEPA. We further show large gains on two applications (interviewer & RAG agents), highlighting that joint graph & configuration search addresses structural failure modes that prompt tuning alone cannot fix.
As the complexity of artificial agents increases, the design of environments that can effectively shape their behavior and capabilities has become a critical research frontier. We propose a framework that extends this principle to a novel class of agents: biological neural networks in the form of neural organoids. This paper introduces three scalable, closed-loop virtual environments designed to train organoid-based biological agents and probe the underlying mechanisms of learning, such as long-term potentiation (LTP) and long-term depression (LTD). We detail the design of three distinct task environments with increasing complexity: (1) a conditional avoidance task, (2) a one-dimensional predator-prey scenario, and (3) a replication of the classic Pong game. For each environment, we formalize the state and action spaces, the sensory encoding and motor decoding mechanisms, and the feedback protocols based on predictable (reward) and unpredictable (punishment) stimulation. Furthermore, we propose a novel meta-learning approach where a Large Language Model (LLM) is used to automate the generation and optimization of experimental protocols, scaling the process of environment and curriculum design. Finally, we outline a multi-modal approach for evaluating learning by measuring synaptic plasticity at electrophysiological, cellular, and molecular levels. This work bridges the gap between computational neuroscience and agent-based AI, offering a unique platform for studying embodiment, learning, and intelligence in a controlled biological substrate.
Progress in many task domains emerges from repeated revisions to previous solution attempts. Training agents that can reliably self-improve over such sequences at inference-time is a natural target for reinforcement learning (RL), yet the naive approach assumes a fixed maximum iteration depth, which can be both costly and arbitrary. We present Exploratory Iteration (ExIt), a family of autocurriculum RL methods that directly exploits the recurrent structure of self-improvement tasks to train LLMs to perform multi-step self-improvement at inference-time while only training on the most informative single-step iterations. ExIt grows a task space by selectively sampling the most informative intermediate, partial histories encountered during an episode for continued iteration, treating these starting points as new self-iteration task instances to train a self-improvement policy. ExIt can further pair with explicit exploration mechanisms to sustain greater task diversity. Across several domains, encompassing competition math, multi-turn tool-use, and machine learning engineering, we demonstrate that ExIt strategies, starting from either a single or many task instances, can produce policies exhibiting strong inference-time self-improvement on held-out task instances, and the ability to iterate towards higher performance over a step budget extending beyond the average iteration depth encountered during training.
We introduce MBTI-in-Thoughts, a framework for enhancing the effectiveness of Large Language Model (LLM) agents through psychologically grounded personality conditioning. Drawing on the Myers-Briggs Type Indicator (MBTI), our method primes agents with distinct personality archetypes via prompt engineering, enabling control over behavior along two foundational axes of human psychology, cognition and affect. We show that such personality priming yields consistent, interpretable behavioral biases across diverse tasks: emotionally expressive agents excel in narrative generation, while analytically primed agents adopt more stable strategies in game-theoretic settings. Our framework supports experimenting with structured multi-agent communication protocols and reveals that self-reflection prior to interaction improves cooperation and reasoning quality. To ensure trait persistence, we integrate the official 16Personalities test for automated verification. While our focus is on MBTI, we show that our approach generalizes seamlessly to other psychological frameworks such as Big Five, HEXACO, or Enneagram. By bridging psychological theory and LLM behavior design, we establish a foundation for psychologically enhanced AI agents without any fine-tuning.
Recent research on Chain-of-Thought (CoT) reasoning in Large Language Models (LLMs) has demonstrated that agents can engage in \textit{complex}, \textit{multi-turn} negotiations, opening new avenues for agentic AI. However, existing LLM agents largely overlook the functional role of emotions in such negotiations, instead generating passive, preference-driven emotional responses that make them vulnerable to manipulation and strategic exploitation by adversarial counterparts. To address this gap, we present EvoEmo, an evolutionary reinforcement learning framework that optimizes dynamic emotional expression in negotiations. EvoEmo models emotional state transitions as a Markov Decision Process and employs population-based genetic optimization to evolve high-reward emotion policies across diverse negotiation scenarios. We further propose an evaluation framework with two baselines -- vanilla strategies and fixed-emotion strategies -- for benchmarking emotion-aware negotiation. Extensive experiments and ablation studies show that EvoEmo consistently outperforms both baselines, achieving higher success rates, higher efficiency, and increased buyer savings. This findings highlight the importance of adaptive emotional expression in enabling more effective LLM agents for multi-turn negotiation.
The emergence of large language models (LLMs) has introduced a new paradigm in automation: LLM agents or Agentic Automation with Computer Use (AACU). Unlike traditional Robotic Process Automation (RPA), which relies on rule-based workflows and scripting, AACU enables intelligent agents to perform tasks through natural language instructions and autonomous interaction with user interfaces. This study investigates whether AACU can serve as a viable alternative to RPA in enterprise workflow automation. We conducted controlled experiments across three standard RPA challenges data entry, monitoring, and document extraction comparing RPA (via UiPath) and AACU (via Anthropic's Computer Use Agent) in terms of speed, reliability, and development effort. Results indicate that RPA outperforms AACU in execution speed and reliability, particularly in repetitive, stable environments. However, AACU significantly reduces development time and adapts more flexibly to dynamic interfaces. While current AACU implementations are not yet production-ready, their promise in rapid prototyping and lightweight automation is evident. Future research should explore multi-agent orchestration, hybrid RPA-AACU architectures, and more robust evaluation across industries and platforms.
The growing demand for scalable psychological counseling highlights the need for fine-tuning open-source Large Language Models (LLMs) with high-quality, privacy-compliant data, yet such data remains scarce. Here we introduce MAGneT, a novel multi-agent framework for synthetic psychological counseling session generation that decomposes counselor response generation into coordinated sub-tasks handled by specialized LLM agents, each modeling a key psychological technique. Unlike prior single-agent approaches, MAGneT better captures the structure and nuance of real counseling. In addition, we address inconsistencies in prior evaluation protocols by proposing a unified evaluation framework integrating diverse automatic and expert metrics. Furthermore, we expand the expert evaluations from four aspects of counseling in previous works to nine aspects, enabling a more thorough and robust assessment of data quality. Empirical results show that MAGneT significantly outperforms existing methods in quality, diversity, and therapeutic alignment of the generated counseling sessions, improving general counseling skills by 3.2% and CBT-specific skills by 4.3% on average on cognitive therapy rating scale (CTRS). Crucially, experts prefer MAGneT-generated sessions in 77.2% of cases on average across all aspects. Moreover, fine-tuning an open-source model on MAGneT-generated sessions shows better performance, with improvements of 6.3% on general counseling skills and 7.3% on CBT-specific skills on average on CTRS over those fine-tuned with sessions generated by baseline methods. We also make our code and data public.
The generation of data is a common approach to improve the performance of machine learning tasks, among which is the training of models for classification. In this paper, we present TAGAL, a collection of methods able to generate synthetic tabular data using an agentic workflow. The methods leverage Large Language Models (LLMs) for an automatic and iterative process that uses feedback to improve the generated data without any further LLM training. The use of LLMs also allows for the addition of external knowledge in the generation process. We evaluate TAGAL across diverse datasets and different aspects of quality for the generated data. We look at the utility of downstream ML models, both by training classifiers on synthetic data only and by combining real and synthetic data. Moreover, we compare the similarities between the real and the generated data. We show that TAGAL is able to perform on par with state-of-the-art approaches that require LLM training and generally outperforms other training-free approaches. These findings highlight the potential of agentic workflow and open new directions for LLM-based data generation methods.
Lexical alignment, where speakers start to use similar words across conversation, is known to contribute to successful communication. However, its implementation in conversational agents remains underexplored, particularly considering the recent advancements in large language models (LLMs). As a first step towards enabling lexical alignment in human-agent dialogue, this study draws on strategies for personalising conversational agents and investigates the construction of stable, personalised lexical profiles as a basis for lexical alignment. Specifically, we varied the amounts of transcribed spoken data used for construction as well as the number of items included in the profiles per part-of-speech (POS) category and evaluated profile performance across time using recall, coverage, and cosine similarity metrics. It was shown that smaller and more compact profiles, created after 10 min of transcribed speech containing 5 items for adjectives, 5 items for conjunctions, and 10 items for adverbs, nouns, pronouns, and verbs each, offered the best balance in both performance and data efficiency. In conclusion, this study offers practical insights into constructing stable, personalised lexical profiles, taking into account minimal data requirements, serving as a foundational step toward lexical alignment strategies in conversational agents.
Reinforcement Learning (RL) has become a pivotal approach for enhancing the reasoning capabilities of Large Language Models (LLMs). However, a significant theoretical gap persists, as traditional token-level RL frameworks fail to align with the reasoning-level nature of complex, multi-step thought processes like Chain-of-Thought (CoT). To address this challenge, we introduce CoT-Space, a novel theoretical framework that recasts LLM reasoning from a discrete token-prediction task to an optimization process within a continuous, reasoning-level semantic space. By analyzing this process from both a noise perspective and a risk perspective, we demonstrate that the convergence to an optimal CoT length is a natural consequence of the fundamental trade-off between underfitting and overfitting. Furthermore, extensive experiments provide strong empirical validation for our theoretical findings. Our framework not only provides a coherent explanation for empirical phenomena such as overthinking but also offers a solid theoretical foundation to guide the future development of more effective and generalizable reasoning agents.
Large language model (LLM) agents achieve impressive single-task performance but commonly exhibit repeated failures, inefficient exploration, and limited cross-task adaptability. Existing reflective strategies (e.g., Reflexion, ReAct) improve per-episode behavior but typically produce ephemeral, task-specific traces that are not reused across tasks. Reinforcement-learning based alternatives can produce transferable policies but require substantial parameter updates and compute. In this work we introduce Meta-Policy Reflexion (MPR): a hybrid framework that consolidates LLM-generated reflections into a structured, predicate-like Meta-Policy Memory (MPM) and applies that memory at inference time through two complementary mechanisms soft memory-guided decoding and hard rule admissibility checks(HAC). MPR (i) externalizes reusable corrective knowledge without model weight updates, (ii) enforces domain constraints to reduce unsafe or invalid actions, and (iii) retains the adaptability of language-based reflection. We formalize the MPM representation, present algorithms for update and decoding, and validate the approach in a text-based agent environment following the experimental protocol described in the provided implementation (AlfWorld-based). Empirical results reported in the supplied material indicate consistent gains in execution accuracy and robustness when compared to Reflexion baselines; rule admissibility further improves stability. We analyze mechanisms that explain these gains, discuss scalability and failure modes, and outline future directions for multimodal and multi?agent extensions.
We investigate the emergent social dynamics of Large Language Model (LLM) agents in a spatially extended El Farol Bar problem, observing how they autonomously navigate this classic social dilemma. As a result, the LLM agents generated a spontaneous motivation to go to the bar and changed their decision making by becoming a collective. We also observed that the LLM agents did not solve the problem completely, but rather behaved more like humans. These findings reveal a complex interplay between external incentives (prompt-specified constraints such as the 60\% threshold) and internal incentives (culturally-encoded social preferences derived from pre-training), demonstrating that LLM agents naturally balance formal game-theoretic rationality with social motivations that characterize human behavior. These findings suggest that a new model of group decision making, which could not be handled in the previous game-theoretic problem setting, can be realized by LLM agents.
In embodied AI, a persistent challenge is enabling agents to robustly adapt to novel domains without requiring extensive data collection or retraining. To address this, we present a world model implanting framework (WorMI) that combines the reasoning capabilities of large language models (LLMs) with independently learned, domain-specific world models through test-time composition. By allowing seamless implantation and removal of the world models, the embodied agent's policy achieves and maintains cross-domain adaptability. In the WorMI framework, we employ a prototype-based world model retrieval approach, utilizing efficient trajectory-based abstract representation matching, to incorporate relevant models into test-time composition. We also develop a world-wise compound attention method that not only integrates the knowledge from the retrieved world models but also aligns their intermediate representations with the reasoning model's representation within the agent's policy. This framework design effectively fuses domain-specific knowledge from multiple world models, ensuring robust adaptation to unseen domains. We evaluate our WorMI on the VirtualHome and ALFWorld benchmarks, demonstrating superior zero-shot and few-shot performance compared to several LLM-based approaches across a range of unseen domains. These results highlight the frameworks potential for scalable, real-world deployment in embodied agent scenarios where adaptability and data efficiency are essential.
Recent significant advancements in Large Language Models (LLMs) have greatly propelled the development of Role-Playing Conversational Agents (RPCAs). These systems aim to create immersive user experiences through consistent persona adoption. However, current RPCA research faces dual limitations. First, existing work predominantly focuses on the textual modality, entirely overlooking critical paralinguistic features including intonation, prosody, and rhythm in speech, which are essential for conveying character emotions and shaping vivid identities. Second, the speech-based role-playing domain suffers from a long-standing lack of standardized evaluation benchmarks. Most current spoken dialogue datasets target only fundamental capability assessments, featuring thinly sketched or ill-defined character profiles. Consequently, they fail to effectively quantify model performance on core competencies like long-term persona consistency. To address this critical gap, we introduce VoxRole, the first comprehensive benchmark specifically designed for the evaluation of speech-based RPCAs. The benchmark comprises 13335 multi-turn dialogues, totaling 65.6 hours of speech from 1228 unique characters across 261 movies. To construct this resource, we propose a novel two-stage automated pipeline that first aligns movie audio with scripts and subsequently employs an LLM to systematically build multi-dimensional profiles for each character. Leveraging VoxRole, we conduct a multi-dimensional evaluation of contemporary spoken dialogue models, revealing crucial insights into their respective strengths and limitations in maintaining persona consistency.
Smartphones have become indispensable in people's daily lives, permeating nearly every aspect of modern society. With the continuous advancement of large language models (LLMs), numerous LLM-based mobile agents have emerged. These agents are capable of accurately parsing diverse user queries and automatically assisting users in completing complex or repetitive operations. However, current agents 1) heavily rely on the comprehension ability of LLMs, which can lead to errors caused by misoperations or omitted steps during tasks, 2) lack interaction with the external environment, often terminating tasks when an app cannot fulfill user queries, and 3) lack memory capabilities, requiring each instruction to reconstruct the interface and being unable to learn from and correct previous mistakes. To alleviate the above issues, we propose MobileRAG, a mobile agents framework enhanced by Retrieval-Augmented Generation (RAG), which includes InterRAG, LocalRAG, and MemRAG. It leverages RAG to more quickly and accurately identify user queries and accomplish complex and long-sequence mobile tasks. Additionally, to more comprehensively assess the performance of MobileRAG, we introduce MobileRAG-Eval, a more challenging benchmark characterized by numerous complex, real-world mobile tasks that require external knowledge assistance. Extensive experimental results on MobileRAG-Eval demonstrate that MobileRAG can easily handle real-world mobile tasks, achieving 10.3\% improvement over state-of-the-art methods with fewer operational steps. Our code is publicly available at: https://github.com/liuxiaojieOutOfWorld/MobileRAG_arxiv