Self-Evolving Agents

Ask about this topic

Overview

Self-evolving agents are systems that use experience from task execution to change how they solve future tasks, rather than relying only on a fixed model or hand-designed workflow. Common approaches store and refine reusable skills or memories, optimize prompts and agent harnesses, train policies with reinforcement learning, or co-evolve task generators, environments, and teams of agents. These methods are tested in settings such as web and GUI use, coding, embodied robotics, scientific workflows, and reasoning benchmarks, with feedback ranging from execution outcomes to verifiers and paired validation. A central challenge is making improvements transfer to new tasks without forgetting earlier abilities or introducing unsafe behavior; reliable evaluation, update verification, and long-term monitoring remain open problems.

Latest papers

CardsList

427 papers104 papers in the last four weeks, up 148% on the four weeks before. 0.6% of all new papers.

Jun 5, 2026

Self-evolving LLM agents with in-distribution Optimization

Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments, yet training them to perform reliable long-horizon decision making remains a fundamental challenge. A key difficulty lies in credit assignment: agents often receive delayed rewards only at the end of episodes. In this paper, we propose Q-Evolve, a self-evolving framework for LLM agents that unifies automatic process-reward labeling and policy learning within a principled in-distribution reinforcement learning paradigm. In each evolving iteration, our method learns an in-distribution critic from a hybrid off-policy dataset that combines expert demonstrations with agent-generated trajectories, stabilizing Bellman backups in sparse-reward settings via a weighted Implicit Q-Learning objective. The learned value function is then used to derive step-wise process rewards through advantage estimation, enabling dense and reliable supervision without environment backtracking or human annotation. Leveraging these signals, we perform behavior-proximal policy optimization that evolves the agent over the data used for process reward labeling, allowing iterative self-improvement without exacerbating distribution shift. We evaluate our method on AlfWorld, WebShop, and ScienceWorld, showing Q-Evolve outperforms strong baselines in sample efficiency, robustness, and overall task performance. Our results demonstrate that stable agent self-evolution is achievable through the co-evolution of process-level supervision and policy, both grounded within a shared in-distribution learning loop.

Yudi Zhang, Meng Fang, Zhenfang Chen +1

Eindhoven University of Technology, Netherlands · University of Liverpool, United Kingdom · MIT-IBM Watson AI Lab.

Reinforcement LearningProcess Reward ModelsCredit Assignment in RLRL for LLM AgentsSelf-Evolving Agents
AskPDF
Jun 5, 2026

FinEvolveBench: A Benchmark for Self-Evolving Agents on Low-Repetition Tasks with Implicit Rewards

Large language model (LLM) agents increasingly rely on external experience to continually adapt to changing environments without modifying their underlying models. Recent experience mechanisms have demonstrated promising results across diverse tasks. However, their effectiveness is typically evaluated within individual benchmark settings, and how experience mechanisms generalize across different scenarios remains insufficiently explored. In this work, we present a scenario-oriented analysis of experience mechanisms for LLM agents. We characterize existing evaluation scenarios along four dimensions: outcome observability, credit assignment complexity, environmental dynamics, and experience reusability. Our analysis shows that existing benchmarks often evaluate experience mechanisms under scenarios where at least one dimension is comparatively favorable, leaving more challenging combinations of scenario properties underexplored. To address this gap, we introduce FinEvolveBench, a reproducible benchmark built on a chronological stream of rich financial news and market data that enables systematic evaluation of experience-based self-evolution under challenging experience regimes characterized by noisy feedback, ambiguous credit assignment, environmental non-stationarity, and limited experience reusability. Experiments show that existing approaches exhibit substantially reduced or inconsistent gains in this setting, highlighting the scenario-dependent nature of experience mechanisms and the challenge of maintaining valid experience under changing environments.

Yining Zhu, Zihao Deng, Leiming Wang +5

Continual Learning for LLM AgentsAI Agent BenchmarksSelf-Evolving Agents
AskPDF
Jun 4, 2026

OpenSkill: Open-World Self-Evolution for LLM Agents

Self-evolving agents requires adaptation after deployment, but existing approaches assume a usable learning loop, such as curated skills, successful trajectories, or verifier signals. Real open-world deployments may provide none of these, offering only a task prompt. In this work, we study open-world self-evolution, where an agent must build both its skills and its own verification signals from scratch, using open-world resources but no target-task supervision. We propose OpenSkill, a framework that bootstraps this loop: it acquires grounded knowledge and verification anchors from documentation, repositories, and the web, synthesizes them into transferable skills, and refines those skills against self-built virtual tasks grounded in the anchors rather than in target answers. The open world thus supplies both the knowledge to be learned and a supervision-independent practice environment, with target-task supervision reserved for final evaluation. Across three benchmarks and two target agents, OpenSkill attains the best automated pass rate while satisfying the no-supervision constraint. Analysis shows its skills transfer across models without model-specific adaptation, and its self-built verifier aligns with ground-truth outcomes despite never accessing them.

Zhiling Yan, Dingjie Song, Hanrong Zhang +8

Lehigh University · University of Illinois Chicago · University of British Columbia +3

LLM Agent Skill LearningLLM Agent VerificationSelf-Evolving Agents
AskPDF
Jun 4, 2026

MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery

Large language model (LLM) agents are increasingly applied to long-horizon tasks such as scientific discovery and machine learning engineering (MLE), where sustained self-evolution becomes a key capability. However, existing MLE agents suffer from isolated exploration, inefficient experience reuse, and lack of hierarchical control, which together hinder long-horizon optimization. We present MLEvolve, an LLM-based self-evolving multi-agent framework for end-to-end machine learning algorithm discovery. By extending tree search to Progressive MCGS, MLEvolve enables cross-branch information flow through graph-based reference edges and gradually shifts the search from broad exploration to focused exploitation with an entropy-inspired progressive schedule. To allow the agent to evolve with accumulated experience, we introduce Retrospective Memory, which combines a cold-start domain knowledge base with a dynamic global memory for task-specific experience retrieval and reuse. For stable long-horizon iteration, we further decouple strategic planning from code generation with adaptive coding modes. Evaluation on MLE-Bench shows that MLEvolve achieves state-of-the-art performance across multiple dimensions including average medal rate and valid submission rate under a 12-hour budget (half the standard runtime). Moreover, MLEvolve also outperforms specialized algorithm discovery methods including AlphaEvolve on mathematical algorithm optimization tasks, demonstrating strong cross-domain generalization. Code is available at https://github.com/InternScience/MLEvolve.

Shangheng Du, Xiangchao Yan, Jinxin Shi +13

Shanghai Artificial Intelligence Laboratory · East China Normal University

Automated Algorithm DiscoveryMulti-Agent LLMsSelf-Evolving AgentsMemory-Augmented Language Model Agents
AskPDF
Jun 4, 2026

Towards Healthy Evolution: Exploring the Role and Mechanisms of Human-Agent Interaction in Self-Evolving Systems

Self-evolving agents improve through continual self-play and self-generated learning signals, but autonomous evolution can also cause capability degradation and safety drift. Although human feedback has proven effective for static and post-trained agents, its role in self-evolving systems remains underexplored. We introduce Agent Norm Correction through Human-like Oversight and Review (ANCHOR), an LLM-based framework that simulates human supervision and delivers feedback at various phases of self-evolution. With ANCHOR, we evaluate two representative open-source self-evolving agent systems across coding, mathematical reasoning, and safety. Our results show that even limited supervision substantially mitigates safety degradation while preserving stable performance on core evolutionary objectives. Further analysis shows that supervision over the output verification phase is the most effective for intervention, whereas increasing supervision frequency yields diminishing returns. These findings provide empirical evidence and practical guidance for designing more stable, controllable, and human-aligned self-evolving agent systems.

Dianxing Shi, Bowen Wang, Junqi He +2

The University of Osaka · Independent researcher

Human-in-the-Loop EvaluationLLM Safety AlignmentLLM Agent SafetySelf-Evolving Agents
AskPDF
Jun 4, 2026

Agentic Software: How AI Agents Are Restructuring the Software Paradigm

For over half a century, software engineering has operated on a foundational premise: human engineers decompose problems, encode decision logic into static code, and manually adapt that code as requirements evolve. This paper argues that the emergence of AI agents -- systems where large language models serve as the primary reasoning engine, dynamically generating and discarding code as an instrumental resource -- constitutes a fundamental restructuring of what software is, not an incremental tool improvement. We formalize the distinction between traditional deterministic software and agentic software: in the former, code is the carrier of pre-written decision logic; in the latter, the agent itself is the software, and its decision logic is generated at runtime. We trace the historical arc from licensed software to SaaS to Agent-as-a-Service (AaaS), showing that each shift transferred additional complexity away from end-users -- with the agentic shift transferring not just operational complexity but decision-making complexity itself. We introduce Agentic Engineering as an expansion of the software engineering discipline into a new paradigm, distinct in its core object of study (agent systems rather than static source code), its control model (LLM-driven rather than human-predefined), and its human role (intent architect rather than code author). Through analysis of recent benchmark evidence including SWE-bench Verified, EvoClaw, and LangChain's multi-agent coordination studies, we demonstrate both the transformative potential of the agentic paradigm and its current limitations. We conclude with a four-stage roadmap toward self-evolving agent ecosystems and concrete recommendations for practitioners navigating this transition.

Zhenfeng Cao

Lingxi Intelligent Investment (Shenzhen) Development Co., Ltd.

Software Engineering AgentsAutomated Software EngineeringAgentic AISelf-Evolving Agents
AskPDF
Jun 3, 2026

EpiEvolve: Self-Evolving Agents for Streaming Pandemic Forecasting under Regime Shifts

Epidemic LLM forecasters are usually trained and evaluated as static supervised models, whereas operational pandemic forecasting is a streaming process in which labels arrive after predictions and disease regimes shift over time. We study this mismatch in weekly COVID-19 hospitalization trend forecasting across five variant regimes. We introduce EpiEvolve, a self-evolving agent that wraps an LLM forecaster trained on the warm-start period and keeps its weights fixed during streaming. EpiEvolve adapts by storing forecast outcomes in a hierarchical episodic memory, reflecting on delayed labels, retrieving cases relevant to the current regime, and distilling recurring errors into strategic rules. The resulting context lets the forecaster reuse its own past predictions and outcomes in later weeks while following a chronological protocol that prevents future leakage. On the streaming dataset, EpiEvolve reaches 0.6290.629 average accuracy, compared with 0.5610.561 for the static backbone and 0.3250.325 for the external CDC ensemble, and reduces recovery lag after regime shifts from 55 to 22 weeks. Ablations show that reflection, strategic memory, and regime-aware retrieval each contribute to the gains.

Yiming Lu, Sihang Zeng, Zhengxu Tang +3

Emory University · University of Washington

Online Time Series ForecastingEpidemic ForecastingTime Series ForecastingLLM-Based Time Series ForecastingNon-Stationary Time Series ForecastingSpatiotemporal Forecasting+2
AskPDF
Jun 3, 2026

VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents

Reusable robot skills are becoming the basic units through which embodied agents turn open-ended instructions into long-horizon physical behavior. We argue that, while foundation models have collapsed the cost of creating these skills, the cost of trusting them has not. Existing skill-evolution loops refine skills through execution feedback, unit tests, environment reward, or LLM self-critique, but these signals provide only trace-level evidence: they show that a skill worked on sampled executions, not that skill-induced plans satisfy temporal safety contracts under untested conditions. We introduce VASO, a framework for verification-guided self-evolution of LLM-generated robot skill contracts. In VASO, each skill is represented as a semantic contract with two coupled interfaces: a formal interface that aligns robot states, observations, and control commands with logical propositions for model checking, and a planner-facing interface that guides executable behavior generation. A model checker first filters logically inconsistent skill contracts, then verifies plans induced by the skill against global and local temporal specifications. When verification fails, VASO translates the counterexample trace into a textual gradient that updates the reusable skill contract while keeping foundation-model weights frozen. On Clearpath Jackal and PX4 quadcopter tasks, VASO reaches 97.2% formal-specification compliance using fewer than 100 optimization samples, outperforming execution-feedback, prompt-optimization, and fine-tuning baselines. To our knowledge, VASO is the first framework that closes the loop between formal verification and self-evolving LLM-generated skills for physical AI agents: formal counterexamples become optimization feedback for reusable robot skill contracts, rather than merely verifying one-off plans, tuning planner prompts, or fine-tuning model weights.

Yunhao Yang, Neel P. Bhatt, Kevin Wang +3

1The University of Texas at Austin · 2Iowa State University

Robot Skill LearningLarge Language Model-Based Robot PlanningFormal VerificationLLM Agent Skill LearningRobot SafetySelf-Evolving Agents+1
AskPDF
Jun 3, 2026

Autonomous heterogeneous catalyst discovery with a self-evolving multi-agent digital twin

Theoretical heterogeneous catalysis promises rapid catalyst discovery, yet computational and machine-learning predictions often deviate from experiment and stay confined to narrow material families, for want of a faithful, condition-aware catalytic simulator. We present CatDT (Catalysis Digital Twin), a self-evolving multi-agent system that builds an autonomous digital twin of a working catalyst, unifying gas-solid and liquid-solid modeling. From only a bulk crystal and a natural-language reaction description, eight specialized agents and 27 scientific tools predict stable facets, reconstruct working surfaces, enumerate and rank reaction pathways, locate transition states, and compute kinetics in 5-30 min on a single GPU. Two innovations address the hardest steps: UniMech finds dominant pathways for novel materials at over 103×10^3\times lower cost than exhaustive enumeration by fusing agent-guided proposals with energy-cached graph search, and a memory-augmented reinforcement loop raises barrier-calculation success from 41% to 84% across 600 catalytic surfaces. Across seven gas-solid benchmarks -- stepped metals, single-atom catalysts, ordered intermetallics, vacancy-rich 2D sulfides and carbides, and a strong-metal--support-interaction (SMSI) interface -- every CatDT prediction lies within 0.5-2 times experiment over four orders of magnitude. For propane dehydrogenation, CatDT independently discovers non-precious candidates rivaling the Pt-based industrial benchmark, with a proposed Ni@ZrO2_2 SMSI overlayer reaching a simulated TOF of 1.63 s−11.63~\text{s}^{-1} at ∼\sim100% selectivity. More broadly, the decisive factor for a faithful catalyst digital twin -- or any multi-stage scientific simulator -- is not raw LLM capability but the engineered harness around it: deterministic tools, persistent memory, and verified self-improvement that compound across models, tools, and runs.

Zhilong Song, Zongmin Zhang, Lixue Cheng

Department of Chemistry, Hong Kong University of Science and Technology, Kowloon, Hong Kong 999077, China · IAS Center for AI for Scientific Discoveries, Hong Kong University of Science and Technology, Kowloon, Hong Kong 999077, China · Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Kowloon, Hong Kong 999077, China +1

Materials ScienceDigital TwinsAutonomous Research AgentsSelf-Evolving Agents
AskPDF
Jun 3, 2026

Scaling Self-Evolving Agents via Parametric Memory

Existing memory-augmented LLM agents store past experience exclusively in prompt space, as textual summaries or retrieved passages, while keeping model parameters frozen throughout a rollout. Such agents can look up what they have seen but cannot learn from it: their policy is unchanged by experience, and any information dropped from the context is permanently lost. We introduce TMEM, a self-evolving parametric memory framework in which the agent not only compresses history into explicit memory but also absorbs distilled supervision into fast LoRA weights ΔtΔ_t via lightweight online updates, genuinely altering its future behavior within a single episode. We formalize this as an agentic decision process with fast-weight rollout dynamics: actions are sampled from πθ0+Δtπ_{θ_0+Δ_t}, while extraction actions produce supervision that updates ΔtΔ_t for subsequent decisions. This view makes the extraction policy directly optimizable by RL: training θ0θ_0 improves not only task actions but also the quality of the data used for online LoRA adaptation. We further propose SVD-based initialization of the LoRA subspace to accelerate online convergence. Experiments on LoCoMo, LongMemEval-S, multi-objective search, and CL-Bench show that TMEM consistently outperforms summary-based and retrieval-based baselines across different model scales.

Tao Ren, Weiyao Luo, Hui Yang +8

Qwen-Character Team · Alibaba Group · Peking University

Online Language Model AdaptationRL for LLM AgentsSelf-Evolving AgentsMemory-Augmented Language Model Agents
AskPDF
Jun 2, 2026

Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents

Large language model (LLM) agents are becoming long-running software actors rather than fixed tool users. They accumulate memory, activate skills, synthesize tools, fork children, attach remote resources, and commit checkpoints into reusable execution images. These mechanisms improve adaptability, but also create a systems-security failure mode: if exposing an action also grants the authority needed to perform it, self-evolution becomes a permission-escalation path. This paper presents Agent libOS, an agent-native library-OS substrate for capability-controlled self-evolving agents. Its central invariant is that model-visible affordances may evolve while resource authority changes only through explicit, audited runtime primitives. Agent libOS represents an agent as an AgentProcess with process identity, process-local Object Memory, message queues, a tool table, loaded Skills, process-local Deno/TypeScript JIT tools, child processes, budgets, checkpoints, and explicit capabilities. AgentImage objects define boot-time prompt and tool-table state; Skills and JIT tools extend the action surface; checkpoint-derived images make internal state reusable. None of these mechanisms grants filesystem, shell, human, memory, process, checkpoint, image, JSON-RPC, MCP, or PTY authority by itself. The prototype implements process-local namespaces, persistent runtime state, LLM-call observability, human approval queues, budgets, syscall-mediated JIT tools, trusted Runtime Modules, Object-bound PTY sessions, checkpoint restore/fork/commit, JSON-RPC and MCP providers, and a deterministic runtime-safety benchmark. On 27 versioned deterministic tasks, it completed the task plans while preventing all modeled unauthorized side effects, with a 7.0% conservative false-denial rate. Simple wrapper and sandbox baselines preserved task completion but failed most safety checks.

Yingqi Zhang

Department of Computer Science and Technology, Tsinghua University Beijing, China

AI Agent SecurityLLM AgentsCapability-Based SecurityTool Access Control for LLM AgentsSelf-Evolving Agents
AskPDF
Jun 2, 2026

EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management

Recent progress in Large Language Model (LLM) agents has enabled promising advances in automated data science. However, existing approaches remain fundamentally limited by their static action sets and lack of principled long-horizon context management, hindering their ability to accumulate reusable experience across tasks and operate reliably in multi-stage, iterative data science pipelines. To address these challenges, we introduce EvoDS, a self-evolving autonomous data science agent that learns to expand its skills and adaptively managing long-term context through agentic reinforcement learning. Specifically, EvoDS introduces two key strategies: (1) Autonomous Skill Acquisition (ASA) mechanism, which enables agents to synthesize, validate, and reuse executable skills; and (2) Adaptive Context Compression (ACC) strategy, which treats context management as a learned control problem rather than passive truncation. These strategies are orchestrated within a two-stage multi-agent training scheme, enabling EvoDS to autonomously improve over time. Theoretically, we prove that EvoDS's hierarchical design reduces tool-selection error, and its optimization objective aligns with an information bottleneck principle, ensuring efficient context use. Empirically, EvoDS outperforms state-of-the-art open-source data science agents by an average of 28.9% across four diverse benchmarks while eliminating out-of-token failures. Our code and data are available at https://github.com/usail-hkust/EvoDS.

Zherui Yang, Fan Liu, Yansong Ning +1

The Hong Kong University of Science and Technology (Guangzhou)

Agentic RLLLM Agent Skill LearningLLM Context ManagementSelf-Evolving Agents
AskPDF
Jun 2, 2026

SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents

Recent AI agents can flexibly invoke skills to solve complex tasks, but their long-term improvement is fundamentally constrained by a lack of systematic skill construction, accumulation, and transfer. In particular, without a unified framework for skill consolidation, agents tend to redundantly construct similar capabilities across different tasks, are unable to effectively transform experience into reusable assets, and struggle to generalize task-specific skills to novel scenarios. To address this limitation, we propose SkillPyramid, a skill consolidation framework that reuses existing skill experience for broader task generalization. Operating on a hierarchical skill topology, SkillPyramid further introduces a self-evolution mechanism that enables agents to compose, validate, and incorporate new skills during task execution. Experiments on ALFWorld, WebShop, and ScienceWorld across four backbone models show that SkillPyramid substantially increases the average reward by 38.0% and reduces execution steps by 27.7%. Overall, our method transforms a skill collection from a static resource pool into a dynamic evolution system.

Yuan Xiong, Ziqi Miao, Qian Chen +6

The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · Shanghai Artificial Intelligence Laboratory, Shanghai, China +1

Lifelong Learning AgentsLLM Agent Skill LearningAgent Skill LearningSelf-Evolving Agents
AskPDF
Jun 2, 2026

EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning

Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and scalar rewards mask diverse failure modes. We introduce EvoTrainer, an autonomous training framework that co-evolves LLM policies and training-side harnesses through empirical feedback: it diagnoses rollout-level evidence, revises diagnostics, backtests interventions, and accumulates reusable skills. Evaluated on mathematical reasoning, competitive-programming code generation, and repository-level software engineering, EvoTrainer matches or exceeds the human-engineered RL references under the same data, codebase, and evaluation protocol, with the largest gain on long-horizon agentic SWE. Trajectory analyses show that retained strategies diverge across domains, evolving diagnostics prevent invalid high-scoring branches from being promoted, and reusable skills shape later search. Autonomous LLM RL should move beyond recipe search toward joint evolution of policies and the training harnesses that interpret them.

Guhong Chen, Yingcheng Shi, Yongbin Li +6

1Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · 2Tongyi Lab , Alibaba Group · 3Alibaba Group +1

RL for Code GenerationAgentic RLReinforcement LearningAgent Harness OptimizationLLM Agent Skill LearningLLM Agent Training+1
AskPDF
Jun 1, 2026

Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions

How can a population of agents self-orchestrate and self-adapt into stronger collective intelligence without centralized control? Inspired by Friedrich Hayek's economic theory of decentralized coordination in markets, we study this question through an agent economy in which agents compete via auctions for the right to act, exchange payments, and accumulate wealth from environmental rewards. These simple local incentives induce decentralized credit assignment, driving global planning without explicit orchestration or communication protocols. The population evolves through economic selection: effective agents accumulate wealth and are mutated via exploitation, while ineffective ones go bankrupt and are replaced via exploration. Using modern Large Language Model (LLM) based agents, we show that, initialized with weak agents, the agent economy produces emergent multi-step reasoning strategies and outperforms stronger monolithic baselines across five agentic tasks, including mathematical reasoning, financial research, scientific research, accelerator design, and distributed-system optimization. Our results suggest a new path to multi-agent intelligence: rather than engineering coordination, we can design decentralized incentive structures under which it automatically emerges.

Zhenting Qi, Huangyuan Su, Ao Qu +13

Harvard · MIT

Multi-Agent CoordinationMulti-Agent ReasoningSelf-Evolving AgentsEmergent Behavior in Multi-Agent Systems
AskPDF
Jun 1, 2026

Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection

Modeling patient trajectories from longitudinal electronic health records (EHRs) requires reasoning over sparse, noisy, and long-context multimodal sequences. Existing LLM-based multi-agent systems address context length but process patients in isolation, failing to mirror how clinicians leverage accumulated experience from similar prior cases. We present Traj-Evolve, a self-evolving multi-agent system with two complementary evolving mechanisms. First, an Experience Pool (ExPool) acts as a non-parametric memory, indexing rejection-sampled reasoning traces to retrieve similar patients as few-shot contexts. Second, multi-agent reinforcement learning (MARL) via reward-ranked fine-tuning parametrically optimizes inter-agent and agent-memory collaboration. A leave-one-out cross-retrieval strategy unifies the two, aligning training- and inference-time behavior under retrieval augmentation. On a lung cancer prediction task utilizing up to five years of multimodal EHRs, Traj-Evolve outperforms 9 strong baselines on the overall population and a challenging never-smoker population. Analysis of the evolving dynamics highlights three key findings: (1) expanding the ExPool shifts optimal retrieval from diverse to specific samples; (2) under MARL, the manager agent's prediction loss converges quickly while the worker agents' temporal reasoning continues to benefit from more verified patients; and (3) the two mechanisms are complementary on the predicted risk, where ExPool improves specificity while MARL improves sensitivity.

Sihang Zeng, Matthew Thompson, Ruth Etzioni +1

University of Washington · Fred Hutch Cancer Center · Google

Retrieval-Augmented GenerationMedical DiagnosisOncologyLongitudinal EHR ModelingMulti-Agent Reinforcement LearningSelf-Evolving Agents+1
AskPDF
Jun 1, 2026

CoMAP: Co-Evolving World Models and Agent Policies for LLM Agents

Equipping language agents with world models enables them to anticipate environment dynamics and evaluate candidate actions before execution. However, existing textual world models are typically fixed after training, preventing them from adapting to the on-policy state-action distributions induced by an evolving agent. Meanwhile, agent-improvement methods often rely on external rewards or verifiers, limiting their applicability in realistic interactive environments. In this paper, we propose COMAP, a novel framework that co-evolves textual world models and agent policies through closed-loop interaction. At each decision step, the world model predicts future state feedback for candidate actions, and the agent performs future-aware reflection by estimating the reliability of this feedback and refining its action accordingly. The resulting on-policy trajectories are then used to update the world model via self-distillation, allowing it to better match the agent's evolving interaction distribution. Across embodied task planning, Web navigation, and tool-use benchmarks, COMAP consistently outperforms competitive baselines, e.g., +16.75% relative improvement with Qwen3-4B. Further analyses show that the co-evolutionary loop improves the world model's prediction accuracy over time and leads to more effective long-horizon decision-making. Our code is available at: https://github.com/loyiv/CoMAP.

Youwei Liu, Jian Wang, Hanlin Wang +1

Central South University · College of Computer Science, Sichuan University · Department of Computing, The Hong Kong Polytechnic University

LLM World ModelsLLM Agent TrainingLong-Horizon LLM AgentsEmbodied World ModelsSelf-Evolving Agents
AskPDF
Jun 1, 2026

Unified Context Evolution for LLM Agents

LLM-based agents can solve multi-step interactive tasks by combining reasoning with environment feedback, yet each episode starts from the same fixed context and any useful strategy discovered along the way is lost once the task ends. Existing approaches either limit learning to the current task or pool all experience into a single untyped store, without distinguishing knowledge types, tracking quality through use, or balancing what the library still lacks. We introduce Unified Context Evolution (UCE), a gradient-free framework that externalizes agent experience into an evolving library of typed Evolvable Context Units (ECUs). UCE decomposes experience into four complementary types (Memory, Strategy, Workflow, and Skill), each generated from trajectories under type-specific conditions, retrieved at decision time, scored through repeated usage outcomes, and pruned when no longer valuable. A scheduling module allocates each cycle's generation budget toward the types where the library is weakest. Across two interactive benchmarks, UCE raises ALFWorld success from 75.4% to 96.3% and WebShop task score from 45.1% to 61.3%, and remains effective across alternative actor reasoning backbones without model retraining.

Zixuan Zhu, Yitong Hu, Yong Dai +4

Nanyang Technological University · Beijing University of Posts and Telecommunications · Fudan University +4

Continual Learning for LLM AgentsLLM Agent Skill LearningSelf-Evolving AgentsMemory-Augmented Language Model Agents
AskPDF
Jun 1, 2026

MetaForge: A Self-Evolving Multimodal Agent that Retrieves, Adapts, and Forges Tools On Demand

Multimodal agents have achieved notable progress on complex reasoning tasks through tool use, yet remain limited by two issues: statically predefined tool inventories fail to generalize to unseen scenarios, and indiscriminate tool invocation incurs redundant cost and noise-induced errors. We propose MetaForge, a multimodal agent framework that learns when to invoke tools and how to evolve its toolset on demand. MetaForge factorizes agentic behavior into four coupled stages: Decide (judging whether tool use is warranted), Retrieve (selecting suitable tools), Adapt (grounding tool parameters in task context), and Forge (synthesizing new skills online and recycling them into the tool library for reuse), forming a closed judge-retrieve-adapt-forge-recycle loop. A unified orchestration policy enables the agent to choose among answering directly, reusing existing tools, or forging new ones. We jointly optimize invocation necessity, retrieval accuracy, execution effectiveness, and forged-skill reusability via reinforcement learning, with an explicit invocation-cost penalty discouraging redundant calls. Across 12 benchmarks, MetaForge consistently surpasses 16 baselines in accuracy, efficiency, and generalization, validating a paradigm shift from static tool inventories to on-demand self-evolution.

Shouang Wei, Houcheng Min, Xinpeng Dong +8

East China Normal University · Zhejiang University · Tsinghua University +2

LLM Agent Skill LearningMultimodal AgentsSelf-Evolving AgentsRL for Tool UseMultimodal Tool Use
AskPDF
Jun 1, 2026

Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams

Auto-harness systems such as A-Evolve, GEPA, and Meta-Harness improve LLM agents by optimizing prompts, skills, tools, memories, and supporting infrastructure from execution feedback, but they are typically evaluated on fixed offline benchmarks. Real deployments instead present open-ended task streams: histories grow without a fixed endpoint, heterogeneous tasks require different harnesses, and problem distributions shift over time. These challenges make a single repeatedly and densely updated harness brittle, causing performance degradation as accuracy peaks early and then declines. This motivates sustained harness construction with task-wise adaptation. We introduce Adaptive Auto-Harness, a framework and system for such streams. The framework decomposes the gap to an oracle harness into evolution loss and adaptation loss. The system addresses these losses with a stateful multi-agent evolver, a harness tree with solve-time routing, and human-steering hooks for cases where history lacks the needed signal. Across prediction-market, security-competition, and event-forecasting streams, Adaptive Auto-Harness outperforms five existing auto-harness baselines and ablations attribute gains to better construction, routing, or targeted human steering. Code is available in Link.

Zewen Liu, Zhan Shi, Yisi Sang +7

Emory University · Amazon · The Pennsylvania State University +2

Continual Learning for LLM AgentsAgent Harness OptimizationLLM Agent Self-ImprovementLLM Agent HarnessesSelf-Evolving Agents
AskPDF
Jun 1, 2026

MobEvolve: An Agentic Self-Evolving Heuristic System for Interpretable Human Mobility Generation

Human mobility generation aims to synthesize realistic trip chains for target populations based on individual features. Existing paradigms, including deep generative models, LLM-based methods, and traditional heuristics, struggle to satisfy the complex demands of this task while simultaneously maintaining interpretability, behavioral plausibility, population-level distributional alignment, and inference efficiency. To bridge this gap, we introduce MobEvolve, the first agentic self-evolving heuristic framework for human mobility generation. MobEvolve initializes a behavior-inspired heuristic system and employs an LLM agent to iteratively evolve its internal logic. By diagnosing empirical misalignments and failure cases on a validation set, the agent proposes targeted updates and accumulates evolution memory for cumulative self-improvement. Extensive evaluations on the Singapore and Montreal benchmarks demonstrate that MobEvolve significantly outperforms state-of-the-art deep generative and LLM-based methods in individual trajectory fidelity, population-level distribution alignment, and behavioral plausibility, while preserving interpretability and high inference efficiency.

Junlin He, Yihong Tang, Tong Nie +6

1The Hong Kong Polytechnic University · 2McGill University · 8Mila – Quebec AI Institute +4

Human Behavior SimulationSelf-Evolving Agents
AskPDF
May 31, 2026

SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems

Recent self-evolving agents have shown that skills can be discovered, refined, and accumulated through execution. However, existing skill-evolution frameworks typically assume a fixed tool layer and evaluate each skill independently, limiting their ability to repair tool-level failures or reason about interactions among skills. We propose SkillSmith, a synergy-aware skill-tool co-evolution framework. SkillSmith introduces a unified proposal space in which reflection produces atomic bundles that jointly modify skills and tools, allowing tools to be wrapped, edited, composed, split, or retired when skill evolution identifies a reusable capability gap. To guide this joint search, SkillSmith maintains an ecological utility model inspired by Lotka-Volterra dynamics, where an interaction matrix estimated from execution traces captures pairwise complementarity and conflict among skills and provides pressure signals for retrieval, mutation prioritization, and retirement. Furthermore, SkillSmith records anti-patterns, including failure signatures, causal attributions, and remedies, to accelerate diagnosis and veto proposals that repeat known mistakes. Experiments on three benchmarks, including WildClawBench, and five Qwen3.5 model scales show that SkillSmith consistently outperforms strong baselines, with gains that amplify as task complexity and multi-skill co-activation increase.

Yangbo Wei, Zhen Huang, Shaoqiang Lu +4

Shanghai Jiao Tong University, Shanghai, China · Eastern Institute of Technology, Ningbo, China · University of Science and Technology of China, Hefei, China +2

Tool-Using AgentsAgent Skill LearningSelf-Evolving Agents
AskPDF
May 30, 2026

MemPro: Agentic Memory Systems as Evolvable Programs

Long-horizon autonomous agents require memory systems to retain historical information, track evolving states, and reuse relevant knowledge beyond finite context windows. Existing agentic memory systems typically follow a memory construction-retrieval (MCR) pipeline, but often adapt mainly the memory bank while keeping the surrounding pipeline fixed after deployment. This fixed-pipeline design struggles to handle heterogeneous task-specific failure modes and can become misaligned with memory banks that evolve in scale and structure over time. To address these limitations, we propose MemPro, a system-level evolution framework that treats the entire MCR pipeline as an evolvable program rather than adapting only the memory bank or prompt text. MemPro maintains a version tree of runnable memory-system implementations, where an Evolving Agent iteratively selects promising versions, diagnoses recurring failures, and creates improved child versions through failure-mode-guided edit-debug refinement. Experiments on LongMemEval, LoCoMo, HotpotQA, and NarrativeQA show that MemPro consistently outperforms strong static and prompt-level evolving baselines within a few iterations, continues to improve with evolution, and achieves a favorable performance-cost trade-off. Code is available at https://github.com/wanghai673/MemPro.

Qingshan Liu, Guoqing Wang, Wen Wu +5

East China Normal University · Xiaohongshu Inc.

Memory-Augmented AgentsAgent Memory ManagementSelf-Evolving Agents
AskPDF
May 29, 2026

MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolution

Large language models (LLMs) exhibit strong reasoning capabilities, yet most LLM-based agents are statically deployed and unable to improve through task interactions. Existing experience-driven methods often rely on memory or heuristics without enhancing the model's ability to learn, treating it as a passive executor and leading to early performance plateaus and limited long-term improvement. To address this issue, we propose MetaEvo, a two-stage framework for continual agent evolution that focuses on improving how the model learns from tasks experience, rather than solely on what it stores. MetaEvo first applies preference-based optimization to enhance the model's ability of principle abstraction, then enables the accumulation and reuse of these principles within a modular agent architecture. Experimental results on diverse reasoning benchmarks demonstrate that MetaEvo consistently outperforms strong baselines, maintains reliable improvement across iterations. These findings validate the effectiveness of meta-optimization in enabling agents to learn from experience and continually enhance their reasoning capabilities.

Bowen Ren, Heyan Huang, Yinghao Li +1

School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China · Beijing Institute of Technology Southeast Academy of Information Technology, Putian, China

Continual Learning for LLM AgentsLLM Agent Self-ImprovementSelf-Evolving Agents
AskPDF
May 28, 2026

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

LLM agents are increasingly deployed as systems built around editable external harnesses, including prompts, skills, memories and tools, that shape task execution without changing model parameters. Harness self-evolution adapts such agents by updating these harnesses from execution evidence. Yet it remains unclear whether a model's base capability in task-solving predicts its capabilities in harness self-evolution: which models produce useful harness updates, and which actually benefit from them? We analyze two harness self-evolution capabilities: (i) harness-updating, the capability to produce useful persistent harness updates from execution evidence; (ii) harness-benefit, the capability to benefit from updated harnesses during task solving. Our analysis reveals two findings. First, harness-updating is flat in base capability: models from different capability tiers produce harness updates that lead to surprisingly similar gains; even Qwen3.5-9B's updates yield gains comparable to those of Claude Opus~4.6. Second, harness-benefit is non-monotonic in base capability: weak-tier models benefit little from updated harnesses, mid-tier models benefit most, and strong-tier models benefit less than mid-tier. We trace low gains at the weak tier to two failure modes: weak-tier models may fail to activate relevant harness artifacts, or activate them but fail to follow them faithfully. These findings suggest investing capability budget in the task-solving agent rather than the evolver, and targeting harness invocation and long-horizon instruction following in agent training. Our source code is publicly available at https://github.com/A-EVO-Lab/a-evolve/tree/release/harness-evolution.

Minhua Lin, Juncheng Wu, Zijun Wang +14

1The Pennsylvania State University · 2UC Santa Cruz · 3Amazon +3

LLM Agent EvaluationAgent Harness OptimizationLLM Agent Self-ImprovementLLM Agent HarnessesSelf-Evolving Agents
AskPDF
May 28, 2026

Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems

LLM-based multi-agent systems (MAS) have emerged as an effective paradigm for complex and long-horizon tasks. However, in real-world tasks, MAS often exhibit various failures during execution and such failures are difficult to eliminate during design. This motivates experience-driven MAS evolution, where a system improves based on its own execution experience. Yet such evolution is challenging because MAS experience is prolonged and intricate, interleaving multiple agents' execution chains and communication messages, which makes it difficult to identify what should be improved. To address this challenge, we propose Meta-Team, an experience-driven MAS evolution framework based on collaborative self-evolution. Meta-Team preserves the execution context of each agent and coordinates post-task communication, enabling agents to exchange distributed evidence for evolution. Building on this design, Meta-Team conducts multi-scale self-evolution, transforming execution experience into reusable improvements to agent behaviors, inter-agent coordination, and team-level organization. Across six long-horizon agent benchmarks, Meta-Team consistently outperforms single-agent systems, hand-crafted MAS, and prior MAS evolution methods; further analyses demonstrate that Meta-Team enables more reliable and scalable MAS self-evolution.

Zhezheng Hao, Tianfu Wang, Huanshuo Dong +7

Zhejiang University · Hong Kong University of Science and Technology · Tencent

Multi-Agent System OptimizationMulti-Agent CoordinationMulti-Agent CollaborationMulti-Agent SystemsLong-Horizon Agent TasksSelf-Evolving Agents
AskPDF
May 28, 2026

PTCG-Bench: Can LLM Agents Master Pokémon Trading Card Game?

Given a strategically complex board game, human players can quickly learn to devise strategies after playing a few rounds. Autonomous agents require similar capabilities in realistic interactive environments, yet existing agent benchmarks often fail to fully capture such strategic and evolving decision-making scenarios. We present PTCG-Bench, a benchmark built on the Pok'{e}mon Trading Card Game (PTCG) that evaluates LLM agents at two complementary levels: (1) their decision-making performance within a single complex environment, and (2) their ability to self-evolving through accumulated experience. We further include a modular harness ablation to better interpret agent performance without conflating it with model capability. Our experiments show that, although LLM agents can achieve non-trivial gameplay performance, sustained and stable self-evolution remains challenging, and performance is sensitive to harness design. We hope that PTCG-Bench will facilitate future research on harness-aware and self-evolving agents in realistic interactive environments.

Dongdong Hua, Yifei Sun, Renhong Huang +3

Zhejiang University · FinVolution Group

Game-Playing AgentsLLM Agent EvaluationAI Agent BenchmarksSelf-Evolving Agents
AskPDF
May 28, 2026

BenchTrace: A Benchmark for Testing Reflection Ability and Controlled Evolution in LLM Agents

Self-evolving agents improve over time by reflecting on past failures, but existing evaluation is limited in two ways: it measures only task scores, leaving reflection quality unknown, and it relies on agents' own episode runs, offering no mechanism to target specific failure patterns. We present BenchTrace, a benchmark for evaluating self-evolution ability in LLM agents. BenchTrace is built on a snapshot-reflection dataset of 1,821 annotated episodes spanning six diverse tasks, and comprises a Reflection Evaluation that probes failure identification through targeted QA tasks, and an Evolution Evaluation that tests whether past failure experience translates into avoidance behavior in a controlled self-evolution simulation. Building on BenchTrace, we propose failure avoidance rate (FAR), a new evaluation metric measuring the fraction of test cases in which the agent successfully avoids the target failure instance. Experiments with Qwen3-32B and GPT-4.1 reveal that both models fall below a 30% end-to-end pass rate on reflection evaluation, with diagnosis as the primary bottleneck. Evolution evaluation shows that self-evolution methods generally improve FAR over the non-evolving baseline, but agents forget early lessons as noise episodes accumulate, and agents fail to generalize their reflections beyond the specific context, causing negative transfer across task contexts. Our correlation analysis further reveals that only a fully correct reflection is strongly associated with higher FAR. BenchTrace exposes concrete limits of current self-evolution approaches and provides a controlled, model-agnostic framework for targeted evaluation.

Jiahao Huang, Fei Cheng, Junfeng Jiang +2

University of Tokyo · Kyoto University · National Institute of Informatics

LLM Agent EvaluationSelf-Reflection in Language Model AgentsAI Agent BenchmarksLLM AgentsSelf-Evolving Agents
AskPDF
May 27, 2026

You Live More Than Once: Towards Hierarchical Skill Meta-Evolving

Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems. Existing works mainly focus on hard-coded skill evolving strategies or parametric learning that rely on expensive parameter updates in the underlying LLMs. In this paper, we demonstrate that test-time refinement of the skill evolving framework itself is necessary for continuous improvement of the agent systems in different downstream scenarios, and lightweight algorithmic adaptation is feasible. Specifically, we propose HiSME, a lightweight hierarchical skill meta-evolving solution that jointly optimizes skills and the skill evolving strategy by learning meta-skills from agents' task execution traces. Experiments on diverse agentic benchmarks show that meta-evolving can produce a higher-quality skill library than pure skill evolving and can derive diverse meta-skills for different scenarios, thereby facilitating future continual experience learning. Our code is temporarily public at https://anonymous.4open.science/r/HiSME-BD45.

Xujun Li, Kehan Zheng, Mingyuan Zhao +7

Department of Computer Science and Technology, Tsinghua University · Huawei Foundation Model Department

Meta-LearningLLM Agent Skill LearningSelf-Evolving Agents
AskPDF
May 27, 2026

ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations

Existing emotional support conversation (ESC) systems mainly rely on end-to-end response generation or coarse strategy supervision, offering limited interpretability and little support for systematic skill improvement. We propose ESC-Skills, a skill-centric framework that discovers and self-evolves executable emotional support skills. We first model localized support interactions as Intervention Units (IUs), which capture state--action--outcome dynamics between seeker states, support interventions, and post-response emotional changes. Based on IUs extracted from both successful and failed ESC dialogues, we construct the ESC-Skills Bank, a repository of executable emotional support skills containing intervention guidance, applicability conditions, expected outcomes, and potential risks. To further improve robustness, we introduce a multi-profile self-evolutionary refinement framework in which an ESC agent interacts with diverse simulated seeker profiles under SAGE evaluation. The resulting interaction traces are analyzed to identify missing skills, unsafe interventions, and profile-specific failure patterns, which are then used to refine the Skills Bank through simulation-based verification. Experimental results demonstrate that ESC-Skills improves both response-level quality and dialogue-level emotional outcomes while providing more interpretable and controllable support behaviors. We will release the code, prompts, and ESC-Skills Bank at https://github.com/aliyun/qwen-dianjin.

Jie Zhu, Huaixia Dou, Shuo Jiang +5

School of Computer Science and Technology, Soochow University · 2Qwen DianJin Team, Alibaba Cloud Computing

Emotional Support ConversationLLM Agent Skill LearningSelf-Evolving Agents
AskPDF