LLM Agent Self-Improvement

LLM: Large Language Model

Ask about this topic

Overview

This field studies how language-model agents can improve across tasks by learning from their own executions, failures, human feedback, or interaction with an environment. Common approaches update prompts, harnesses, skills, memory, or tools while keeping model weights fixed; others use reinforcement learning, self-distillation, or co-evolving tasks and agents. Methods often analyze trajectories to diagnose weaknesses, then test candidate changes with benchmarks, paired comparisons, or held-out regression gates. A central challenge is making gains transfer to new settings without eroding previously reliable behavior, while keeping evaluation trustworthy and improvement costs manageable.

Latest papers

CardsList

277 papers73 papers in the last four weeks, up 121% on the four weeks before. 0.4% of all new papers.

May 8, 2026

SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents

Skill libraries have become a practical way for LLM agents to reuse procedural experience across tasks. However, existing systems typically treat skills as flat, single-resolution prompt blocks. This creates a tension between relevance and cost: injecting coarse skills can introduce irrelevant or misleading context, while rewriting entire skills is expensive and often unnecessary. We propose SkillLens, a hierarchical skill-evolution framework that organizes skills into a four-layer graph of policies, strategies, procedures, and primitives, and retrieves them at mixed granularity. Given a task, SkillLens first retrieves semantically relevant skill seeds, expands them through degree-corrected random walk over the skill graph, and then uses a verifier to decide whether each visited unit should be accepted, decomposed, rewritten, or skipped. This enables the agent to reuse compatible subskills directly while adapting only locally mismatched components. To improve the system over time, SkillLens further refines multi-granularity skills and verifier in order to improve its routing decisions. We provide theoretical analysis showing that mixed-granularity adaptation incurs sublinear cost under sparse mismatch assumptions and that the evolutionary update rule monotonically improves the validation objective until a local optimum. Across MuLocbench and ALFWorld, SkillLens consistently improves over strong skill-based baselines, achieving up to a 6.31 percentage-point Acc@1 gain for bug localization and raising agent success rate from 45.00% to 51.31%.

Ziyang Yu, Yongliang Miao, Liang Zhao +2

Emory University

LLM Agent Self-ImprovementLLM Agent Skill LearningGraph-Based RetrievalLLM Agent Skill Retrieval
AskPDF
May 7, 2026

SHARP: A Self-Evolving Human-Auditable Rubric Policy for Financial Trading Agents

Large language models (LLMs) are increasingly deployed for autonomous financial trading, a domain requiring continuous adaptation to noisy, non-stationary markets. Existing self-improving agents typically address this through unbounded free-form prompt optimization. However, in low signal-to-noise environments with delayed scalar rewards (P&L), this unstructured approach exacerbates the fundamental credit assignment problem: optimizers cannot reliably distinguish systematic logic flaws from stochastic market variance, inevitably leading to policy drift. To overcome this bottleneck, we introduce the Self-Evolving Human-Auditable Rubric Policy (SHARP), a neuro-symbolic framework that replaces unconstrained text mutation with structured, symbolic policy optimization. SHARP confines the agent's reasoning to a bounded, human-readable rubric of explicit condition-action rules. When sub-optimal trades occur, an attribution agent employs cross-sample reasoning across multiple samples to isolate specific rule failures. This enables targeted, atomic policy edits that are subsequently regularized through strict walk-forward validation. Evaluated across three diverse equity sectors and four LLM backbones, SHARP consistently transforms generic initial heuristics into highly robust strategies, lifting the empirical performance of compact models by 10 to 20 percentage points on average (e.g., GPT-4o-mini). Ultimately, SHARP demonstrates that LLMs can achieve dynamic and efficient adaptation while significantly enhancing the structural transparency and auditability demanded by institutional finance.

Xiwen Chen, Wenhui Zhu, Songzhu Zheng +3

Morgan Stanley · Arizona State University · Columbia University +1

Reinforcement LearningCredit Assignment in RLLLM Agent Self-ImprovementAlgorithmic Trading
AskPDF
May 7, 2026

TheraAgent: Self-Improving Therapeutic Agent for Precise and Comprehensive Treatment Planning

Formulating a treatment plan is inherently a complex reasoning and refinement task rather than a simple generation problem. However, existing large language models (LLMs) mainly rely on one-shot output without explicit verification, which may result in rough, incomplete, and potentially unsafe treatment plans. To address these limitations, we propose TheraAgent, an agentic framework that replaces one-shot generation with an iterative generate-judge-refine pipeline. By mirroring the actual reasoning process of human experts who iteratively revise treatment plans, our framework progressively transforms coarse and incomplete drafts into precise, comprehensive, and safer therapeutic regimens. To facilitate the critical judge component, we introduce TheraJudge, a treatment-specific evaluation module integrated into the inference loop to enforce clinical standards. Experiments show TheraAgent achieves state-of-the-art results on HealthBench, leading in Accuracy and Completeness. In expert evaluations, it attains an 86% win rate against physicians, with superior Targeting and Harm Control. Moreover, the highly agreement between TheraJudge and HealthBench evaluations confirms the reliability of our framework.

Junkai Li, Yunghwei Lai, Tianyi Zhu +3

1Dept. of Comp. Sci. & Tech., Institute for AI, Tsinghua University, Beijing, China · Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China · School of Computing, National University of Singapore, Singapore

LLM Self-RefinementHealthcareLLM Agent Self-ImprovementClinical Language Model EvaluationLLM Agent Safety
AskPDF
May 4, 2026

ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning

LLM-based agents can recover from individual execution errors, yet they repeatedly fail on the same fault when the underlying process knowledge--operator schemas, preconditions, and constraints--remains unrepaired. Existing self-evolving approaches address this gap by updating prompts, memory, or model weights, but none directly repair the symbolic structures that encode how tasks are executed, and few provide the governance guarantees required for safe deployment. We introduce ANNEAL, a neuro-symbolic agent that converts recurring failures into governed symbolic edits of a process knowledge graph without modifying foundation model weights. Its core mechanism, Failure-Driven Knowledge Acquisition (FDKA), localizes the responsible operator, synthesizes a typed patch through constrained LLM generation, and validates the proposal via multi-dimensional scoring, symbolic guardrails, and canary testing before commit. Every accepted edit carries full provenance and deterministic rollback capability. Across four domains and 27 multi-seed runs, ANNEAL is the only evaluated system that commits persistent structural repairs--strong baselines such as ReAct and Reflexion achieve high episodic recovery yet retain 72--100% holdout failure rates on recurring faults, whereas ANNEAL reduces these to 0% in the tested recurring-failure settings. Ablation confirms that removing FDKA eliminates all structural repairs and drops success rate by up to 26.7 percentage points. These results suggest that governed symbolic repair offers a complementary paradigm to weight-level and prompt-level adaptation for persistent fault elimination.

Safayat Bin Hakim, Keyan Guo, Wenkai Tan +3

University of Maryland, Baltimore County · University at Buffalo · University of Colorado Boulder +1

LLM Agent Self-ImprovementAI Agent GovernanceNeuro-Symbolic AIKnowledge Graphs
AskPDF
Apr 30, 2026

Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO

We introduce Skills-Coach, a novel automated framework designed to significantly enhance the self-evolution of skills within Large Language Model (LLM)-based agents. Addressing the current fragmentation of the skill ecosystem, Skills-Coach explores the boundaries of skill capabilities, thereby facilitating the comprehensive competency coverage essential for intelligent applications. The framework comprises four core modules: a Diverse Task Generation Module that systematically creates a comprehensive test suite for various skills; a Lightweight Optimization Module dedicated to optimizing skill prompts and their corresponding code; a Comparative Execution Module facilitating the execution and evaluation of both original and optimized skills; and a Traceable Evaluation Module, which rigorously evaluates performance against specified criteria. Skills-Coach offers flexible execution options through its virtual and real modes. To validate its efficacy, we introduce Skill-X, a comprehensive benchmark dataset consisting of 48 diverse skills. Experimental results demonstrate that Skills-Coach achieves significant performance improvements in skill capability across a wide range of categories, highlighting its potential to advance the development of more robust and adaptable LLM-based agents.

Yu Tian, Jiawei Chen, Lifan Zheng +5

University of Chinese Academy of Sciences · 2East China Normal University · 3Zhongguancun Academy +3

LLM Agent Self-ImprovementLLM Agent Skill LearningPrompt Optimization
AskPDF
Apr 29, 2026

Self-Evolving Software Agents

Autonomous agents can adapt their behaviour to changing environments, but remain bound to requirements, goals, and capabilities fixed at design time, preventing genuine software evolution. This paper introduces self-evolving software agents, combining BDI reasoning with LLMs to enable autonomous evolution of goals, reasoning, and executable code. We propose a BDI-LLM architecture in which an automated evolution module operates alongside the agent's reasoning loop, eliciting new requirements from experience and synthesizing corresponding design and code updates. A prototype evaluated in a dynamic multi-agent environment shows that agents can autonomously discover new goals and generate executable behaviours from minimal prior knowledge. The results indicate both the feasibility and current limits of LLM-driven evolution, particularly in terms of behavioural inheritance and stability.

Marco Robol, Paolo Giorgini

University of Trento · Trento, Italy

Software Engineering AgentsLLM Agent Self-ImprovementAgentic AISelf-Evolving Agents
AskPDF
Apr 29, 2026

SiriusHelper: An LLM Agent-Based Operations Assistant for Big Data Platforms

Big data platforms are widely used in modern enterprises, and an in-production intelligent assistant is increasingly important to help users quickly find actionable guidance and reduce operational burden. While recent LLM+RAG assistants provide a natural interface, they face practical challenges in real deployments: limited scenario coverage across both general consultation and domain-specific troubleshooting workflows, inefficient knowledge access due to inadequate multi-hop retrieval and flat knowledge organization, and high maintenance cost because escalated tickets are unstructured and hard to convert into assistant improvements and reusable SOPs. In this paper, we present SiriusHelper, a deployed intelligent assistant for big data platforms. SiriusHelper serves as a unified online assistant that automatically identifies user intent and routes queries to the right handling path, including dedicated expert workflows for specialized scenarios (e.g., SQL execution diagnosis). To support complex troubleshooting, SiriusHelper combines a DeepSearch-driven mechanism with a priority-based hierarchical knowledge base to enable multi-hop retrieval without context overload, thus improving answer reliability and latency. To reduce expert overhead, SiriusHelper further introduces automated ticket understanding and SOP distillation: it diagnoses the assistant failure reason (e.g., missing knowledge or wrong routing) and extracts domain-specific SOPs to continuously enrich the knowledge base. Experiments and online deployment on Tencent Big Data platform show that SiriusHelper outperforms representative alternatives and reduces online ticket volume by 20.8%.

Yu Shen, Shiyang Liu, Qihang He +14

TEG, Tencent Inc., China · School of Computer Science, Peking University, China

Customer Support AutomationLLM Agent OrchestrationLLM Agent Self-ImprovementLLM Agents
AskPDF
Apr 23, 2026

AEL: Agent Evolving Learning for Open-Ended Environments

LLM agents increasingly operate in open-ended environments spanning hundreds of sequential episodes, yet they remain largely stateless: each task is solved from scratch without converting past experience into better future behavior. The central obstacle is not what to remember but how to use what has been remembered, including which retrieval policy to apply, how to interpret prior outcomes, and when the current strategy itself must change. We introduce Agent Evolving Learning (\ael{}), a two-timescale framework that addresses this obstacle. At the fast timescale, a Thompson Sampling bandit learns which memory retrieval policy to apply at each episode; at the slow timescale, LLM-driven reflection diagnoses failure patterns and injects causal insights into the agent's decision prompt, giving it an interpretive frame for the evidence it retrieves. On a sequential portfolio benchmark (10 sector-diverse tickers, 208 episodes, 5 random seeds), \ael{} achieves a Sharpe ratio of 2.13±\pm0.47, outperforming five published self-improving methods and all non-LLM baselines while maintaining the lowest variance among all LLM-based approaches. A nine-variant ablation reveals a ``less is more'' pattern: memory and reflection together produce a 58% cumulative improvement over the stateless baseline, yet every additional mechanism we test (planner evolution, per-tool selection, cold-start initialization, skill extraction, and three credit assignment methods) degrades performance. This demonstrates that the bottleneck in agent self-improvement is self-diagnosing how to use experience rather than adding architectural complexity. Code and data: https://github.com/WujiangXu/AEL.

Wujiang Xu, Jiaojiao Han, Minghao Guo +4

Rutgers University · Independent Researcher

LLM Agent Self-ImprovementLLM AgentsMemory-Augmented Language Model Agents
AskPDF
Apr 22, 2026

The Last Harness You'll Ever Build

AI agents are increasingly deployed on complex, domain-specific workflows -- navigating enterprise web applications that require dozens of clicks and form fills, orchestrating multi-step research pipelines that span search, extraction, and synthesis, automating code review across unfamiliar repositories, and handling customer escalations that demand nuanced domain knowledge. Each new task domain requires painstaking, expert-driven harness engineering: designing the prompts, tools, orchestration logic, and evaluation criteria that make a foundation model effective. We present a two-level framework that automates this process. At the first level, the Harness Evolution Loop optimizes a worker agent's harness H\mathcal{H} for a single task: a Worker Agent WHW_{\mathcal{H}} executes the task, an Evaluator Agent VV adversarially diagnoses failures and scores performance, and an Evolution Agent EE modifies the harness based on the full history of prior attempts. At the second level, the Meta-Evolution Loop optimizes the evolution blueprint Λ=(WH,H(0),V,E)Λ= (W_{\mathcal{H}}, \mathcal{H}^{(0)}, V, E) itself across diverse tasks, \textbf{learning a blueprint Λ(best)Λ^{(\text{best})} that enables rapid harness convergence on any new task -- so that adapting an agent to a novel domain requires no human harness engineering at all.} We formalize the correspondence to meta-learning and present both algorithms. The framework shifts manual harness engineering into automated harness engineering, and takes one step further -- automating the design of the automation itself.

Haebin Seong, Li Yin, Haoran Zhang +1

Meta-LearningAgent Harness OptimizationLLM Agent Workflow OptimizationLLM Agent Self-ImprovementLLM Agent HarnessesSelf-Evolving Agents
AskPDF
Apr 20, 2026

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration

Most agents today ``self-evolve'' by following rewards and rules defined by humans. However, this process remains fundamentally dependent on external supervision; without human guidance, the evolution stops. In this work, we train agents to possess an intrinsic meta-evolution capability to spontaneously learn about unseen environments prior to task execution. To instill this ability, we design an outcome-based reward mechanism that measures how much an agent's self-generated world knowledge improves its success rate on downstream tasks. This reward signal is used exclusively during the training phase to teach the model how to explore and summarize effectively. At inference time, the agent requires no external rewards or human instructions. It spontaneously performs native self-evolution to adapt to unknown environments using its internal parameters. When applied to Qwen3-30B and Seed-OSS-36B, this shift to native evolution yields a 20% performance increase on WebVoyager and WebWalker. Most strikingly, the generated world knowledge even enables a compact 14B Qwen3 model to outperform the unassisted Gemini-2.5-Flash, establishing a new paradigm for truly evolving agents.

Qifan Zhang, Dongyang Ma, Tianqing Fang +5

1Tencent · 2The Hong Kong University of Science and Technology (Guangzhou)

Intrinsic MotivationLLM Agent Self-ImprovementLLM Agent TrainingSelf-Evolving Agents
AskPDF
Apr 16, 2026

Autogenesis: A Self-Evolving Agent Protocol

LLM-based agent systems can adapt by revising prompts, constructing tools, and changing other runtime resources. Managing these heterogeneous updates requires a shared lifecycle for identifying targets, assessing candidates, and retaining accepted versions, complementing communication protocols such as A2A and MCP. We introduce AUTOGENESIS PROTOCOL (AGP), which decouples what evolves from how updates are proposed. Its Resource Substrate Protocol Layer (RSPL) represents prompts, agents, tools, environments, and memory as protocol-registered resources with explicit state and versioned interfaces. Its Self-Evolution Protocol Layer (SEPL) specifies candidate proposal, assessment, and commit, with auditable histories and support for restoring retained resource states. We instantiate AGP in AUTOGENESIS SYSTEM (AGS), a self-evolving multi-agent system that retrieves, instantiates, and refines resources during execution. Across reasoning, tool-use, and coding benchmarks, AGS improves over its non-evolving configuration, and repeated reasoning runs report the accompanying output-token cost. Execution cases show a shared update lifecycle across all five resource types.

Wentao Zhang, Zhe Zhao, Haibin Wen +4

Nanyang Technological University · Stanford University · City University of Hong Kong +1

Multi-Agent LLM SystemsLLM Agent Self-ImprovementLLM AgentsLong-Horizon Agent TasksSelf-Evolving Agents
AskPDF
Apr 15, 2026

Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improve

Tool-augmented large language model (LLM) agents can orchestrate specialist classifiers, segmentation models, and visual question-answering modules to interpret chest X-rays. However, these agents still solve each case in isolation: they fail to accumulate experience across cases, correct recurrent reasoning mistakes, or adapt their tool-use behavior without expensive reinforcement learning. While a radiologist naturally improves with every case, current agents remain static. In this work, we propose Evo-MedAgent, a self-evolving memory module that equips a medical agent with the capacity for inter-case learning at test time. Our memory comprises three complementary stores: (1)~Retrospective Clinical Episodes that retrieve problem-solving experiences from similar past cases, (2)~an Adaptive Procedural Heuristics bank curating priority-tagged diagnostic rules that evolves via reflection, much like a physician refining their internal criteria, and (3)~a Tool Reliability Controller that tracks per-tool trustworthiness. On ChestAgentBench, Evo-MedAgent raises multiple-choice question (MCQ) accuracy from 0.68 to 0.79 on GPT-5-mini, and from 0.76 to 0.87 on Gemini-3 Flash. With a strong base model, evolving memory improves performance more effectively than orchestrating external tools on qualitative diagnostic tasks. Because Evo-MedAgent requires no training, its per-case overhead is bounded by one additional retrieval pass and a single reflection call, making it deployable on top of any frozen model.

Weixiang Shen, Bailiang Jian, Jun Li +6

Technical University of Munich (TUM) · TUM University Hospital · LMU Munich +3

Medical AI AgentsLLM Agent Self-ImprovementLLM Agent MemoryContinual Learning for LLM AgentsLLM Agent OrchestrationMedical Image Analysis
AskPDF
Apr 13, 2026

Mem2^2Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation

While large language model--powered agents can self-evolve by accumulating experience or by dynamically creating new assets (i.e., tools or expert agents), existing frameworks typically treat these two evolutionary processes in isolation. This separation overlooks their intrinsic interdependence: the former is inherently bounded by a manually predefined static toolset, while the latter generates new assets from scratch without experiential guidance, leading to limited capability growth and unstable evolution. To address this limitation, we introduce a novel paradigm of co-evolutionary Capability Expansion and Experience Distillation. Guided by this paradigm, we propose the \textbf{Mem2^{\textbf{2}}Evolve}, which integrates two core components: Experience Memory and Asset Memory. Specifically, Mem2^{2}Evolve leverages accumulated experience to guide the dynamic creation of assets, thereby expanding the agent's capability space while simultaneously acquiring new experience to achieve co-evolution. Extensive experiments across 6 task categories and 8 benchmarks demonstrate that Mem2^{2}Evolve achieves improvement of 18.53% over standard LLMs, 11.80% over agents evolving solely through experience, and 6.46% over those evolving solely through asset creation, establishing it as a substantially more effective and stable self-evolving agent framework. Code is available at: https://buaa-irip-llm.github.io/Mem2Evolve.

Zihao Cheng, Zeming Liu, Yingyu Shan +7

Beihang University · Beijing Institute of Technology · Independent Researcher +2

LLM Agent Self-ImprovementSelf-Evolving AgentsTool-Augmented Language Model AgentsMemory-Augmented Language Model Agents
AskPDF
Apr 12, 2026

Semantic Feature Analysis: Improving Agents Without Searching Over Rollouts

Ambiguity is an inherent property of natural-language agent specifications. When a system prompt leaves behaviour underdetermined, identical inputs follow divergent execution paths and produce inconsistent outcomes. The standard remedy is prompt optimisation: propose candidate prompts, run the agent to score them, and keep the best. This loop pays for the agent twice: once to generate candidates and again to rank them. On a tool-using agent whose rollouts cost dollars and minutes, the ranking cost dominates and budget-constrained optimisers routinely fail to find improvements. We present Semantic Feature Analysis (SFA), a pipeline that repairs agent specifications without running any search. SFA reads execution traces the agent has already produced, clusters the outputs of each workflow node, decomposes them into semantic feature classes using an extended subject-verb-object schema, ranks those features by their contribution to outcome separation using a decision tree, and injects the surviving features as corrective statements into the affected node's system prompt. Because it never ranks candidate prompts, it never spends a rollout on selection. We evaluate SFA against five prompt optimisers (GEPA, MIPROv2, SIMBA, BootstrapFewShot with random search, InferRules) and a single-reflection control, budget-matched in dollars at three budget levels across four benchmarks (IF-Bench, HotpotQA, HoVer, and GAIA). SFA consistently improves over the unmodified agent across benchmarks and budget levels, with the largest gains where rollouts are most expensive. On GAIA, where budget-constrained optimisers cannot afford to score even one candidate, SFA improves accuracy while other arms return their seed unchanged.

Yuval David, Fabiana Fournier, Lior Limonad +1

IBM Software Innovation Lab Haifa, Israel

LLM Agent Self-ImprovementTool-Using AgentsPrompt Optimization
AskPDF
Apr 9, 2026

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment. As a result, similar workflows, tool usage patterns, and failure modes are repeatedly rediscovered across users, preventing the system from improving with experience. While interactions from different users provide complementary signals about when a skill works or fails, existing systems lack a mechanism to convert such heterogeneous experiences into reliable skill updates. To address these issues, we present SkillClaw, a framework for collective skill evolution in multi-user agent ecosystems, which treats cross-user and over-time interactions as the primary signal for improving skills. SkillClaw continuously aggregates trajectories generated during use and processes them with an autonomous evolver, which identifies recurring behavioral patterns and translates them into updates to the skill set by refining existing skills or extending them with new capabilities. The resulting skills are maintained in a shared repository and synchronized across users, allowing improvements discovered in one context to propagate system-wide while requiring no additional effort from users. By integrating multi-user experience into ongoing skill updates, SkillClaw enables cross-user knowledge transfer and cumulative capability improvement, and experiments on WildClawBench show that limited interaction and feedback, it significantly improves the performance of Qwen3-Max in real-world agent scenarios.

Ziyu Ma, Shidong Yang, Yuxiang Ji +5

DreamX Team, Alibaba Group

LLM Agent Skill LearningLLM Agent Self-ImprovementContinual Learning for LLM Agents
AskPDF
Apr 9, 2026

SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support

Deploying LLM-powered agents in enterprise scenarios such as cloud technical support demands high-quality, domain-specific skills. However, existing skill creators lack domain grounding, producing skills poorly aligned with real-world task requirements. Moreover, once deployed, there is no systematic mechanism to trace execution failures back to skill deficiencies and drive targeted refinements, leaving skill quality stagnant despite accumulating operational evidence. We introduce SkillForge, a self-evolving framework that closes an end-to-end creation-evaluation-refinement loop. To produce well-aligned initial skills, a Domain-Contextualized Skill Creator grounds skill synthesis in knowledge bases and historical support tickets. To enable continuous self-optimization, a three-stage pipeline -- Failure Analyzer, Skill Diagnostician, and Skill Optimizer -- automatically diagnoses execution failures in batch, pinpoints the underlying skill deficiencies, and rewrites the skill to eliminate them. This cycle runs iteratively, allowing skills to self-improve with every round of deployment feedback. Evaluated on five real-world cloud support scenarios spanning 1,883 tickets and 3,737 tasks, experiments show that: (1) the Domain-Contextualized Skill Creator produces substantially better initial skills than the generic skill creator, as measured by consistency with expert-authored reference responses from historical tickets; and (2) the self-evolution loop progressively improves skill quality from diverse starting points (including expert-authored, domain-created, and generic skills) across successive rounds, demonstrating that automated evolution can surpass manually curated expert knowledge.

Xingyan Liu, Xiyue Luo, Linyu Li +3

Alibaba Cloud Computing, Alibaba Group

LLM Agent Skill EvaluationLLM Agent Self-ImprovementLLM Agent Skill LearningContinual Learning for LLM Agents
AskPDF
Apr 7, 2026

TRACE: Capability-Targeted Agentic Training

Models often fail to complete agentic tasks because they lack core capabilities required by the target environment. However, mainstream approaches for addressing these failures typically either fine-tune directly on target environments or generate synthetic data that is not targeted to the model's actual capability deficits, resulting in low sample efficiency and limited generalization. We introduce TRACE (Turning Recurrent Agent failures into Capability-targeted training Environments), an end-to-end system for environment-specific agent self-improvement. TRACE contrasts successful and failed trajectories to automatically identify missing capabilities, synthesizes a targeted training environment for each capability that rewards whether the capability is exercised, trains a LoRA adapter via reinforcement learning on each synthetic environment, and then trains a mixture-of-experts model over the capability adapters. TRACE can be effectively applied across different environments, improving over the base agent by +15.3 points on τ2τ^2-Bench, a customer-service agent benchmark, and by +15.0 points Pass@1 on SWE-Bench Verified, a software-engineering benchmark. TRACE outperforms the strongest external baselines, GEPA and SWE-RL, by +8.6 points and +8.4 points, respectively. In addition, TRACE is more sample-efficient than strong fine-tuning baselines: using fewer than one-fourth the number of rollouts, TRACE outperforms the best-performing baselines, GRPO and GEPA, and achieves higher final accuracy by +10.4 and +8.6 points on τ2τ^2-Bench.

Hangoo Kang, Tarun Suresh, Jon Saad-Falcon +1

Stanford University

LLM Agent Self-ImprovementAgent Skill LearningSample-Efficient RLRL for LLM Agents
AskPDF
Apr 5, 2026

Combee: Scaling Prompt Learning for Self-Improving Language Model Agents

Recent advances in prompt learning allow large language model agents to acquire task-relevant knowledge from inference-time context without parameter changes. For example, existing methods (like ACE or GEPA) can learn system prompts to improve accuracy based on previous agent runs. However, these methods primarily focus on single-agent or low-parallelism settings. This fundamentally limits their ability to efficiently learn from a large set of collected agentic traces. It would be efficient and beneficial to run prompt learning in parallel to accommodate the growing trend of learning from many agentic traces or parallel agent executions. Yet without a principled strategy for scaling, current methods suffer from quality degradation with high parallelism. To improve both the efficiency and quality of prompt learning, we propose Combee, a novel framework to scale parallel prompt learning for self-improving agents. Combee speeds up learning and enables running many agents in parallel while learning from their aggregate traces without quality degradation. To achieve this, Combee leverages parallel scans and employs an augmented shuffle mechanism; Combee also introduces a dynamic batch size controller to balance quality and delay. Evaluations on AppWorld, Terminal-Bench, Formula, and FiNER demonstrate that Combee achieves up to 17x speedup over previous methods with comparable or better accuracy and equivalent cost.

Hanchen Li, Runyuan He, Qizheng Zhang +11

UC Berkeley · Stanford University · Independent +1

LLM Input OptimizationLLM PromptingLLM Agent Self-Improvement
AskPDF
Apr 5, 2026

SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources

Modern scientific ecosystems are rich in procedural knowledge across repositories, APIs, scripts, notebooks, documentation, databases, and papers, yet much of this knowledge remains fragmented across heterogeneous artifacts that agents cannot readily operationalize. This gap between abundant scientific know-how and usable agent capabilities is a key bottleneck for building effective scientific agents. We present SkillFoundry, a self-evolving framework that converts such resources into validated agent skills, reusable packages that encode task scope, inputs and outputs, execution steps, environment assumptions, provenance, and tests. SkillFoundry organizes a target domain as a domain knowledge tree, mines resources from high-value branches, extracts operational contracts, compiles them into executable skill packages, and then iteratively expands, repairs, merges, or prunes the resulting library through a closed-loop validation process. SkillFoundry produces a substantially novel and internally valid skill library, with 71.1% of mined skills differing from existing skill libraries such as SkillHub and SkillSMP. We demonstrate that these mined skills improve coding agent performance on five of the six MoSciBench datasets. We further show that SkillFoundry can design new task-specific skills on demand for concrete scientific objectives, and that the resulting skills substantially improve performance on two challenging genomics tasks: cell type annotation and the scDRS workflow. Together, these results show that automatically mined skills improve agent performance on benchmarks and domain-specific tasks, expand coverage beyond hand-crafted skill libraries, and provide a practical foundation for more capable scientific agents.

Shuaike Shen, Wenduo Cheng, Mingqian Ma +3

Ray and Stephanie Lane Computational Biology Department, School of Computer Science, Carnegie Mellon University · Machine Learning Department, School of Computer Science, Carnegie Mellon University

Agent Skill LearningAI Agents for Scientific DiscoveryLLM Agent Self-Improvement
AskPDF
Apr 3, 2026

Reflective Context Learning: Studying the Optimization Primitives of Context Space

Generally capable agents must learn from experience in ways that generalize across tasks and environments. The fundamental problems of learning, including credit assignment, overfitting, forgetting, local optima, and high-variance learning signals, persist whether the learned object lies in parameter space or context space. While these challenges are well understood in classical machine learning optimization, they remain underexplored in context space, leading current methods to be fragmented and ad hoc. We present Reflective Context Learning (RCL), a unified framework for agents that learn through repeated interaction, reflection on behavior and failure modes, and iterative updates to context. In RCL, reflection converts trajectories and current context into a directional update signal analogous to gradients, while mutation applies that signal to improve future behavior in context space. We recast recent context-optimization approaches as instances of this shared learning problem and systematically extend them with classical optimization primitives, including batching, improved credit-assignment signal, auxiliary losses, failure replay, and grouped rollouts for variance reduction. On AppWorld, BrowseComp+, and RewardBench2, these primitives improve over strong baselines, with their relative importance shifting across task regimes. We further analyze robustness to initialization, the effects of batch size, sampling and curriculum strategy, optimizer-state variants, and the impact of allocating stronger or weaker models to different optimization components. Our results suggest that learning through context updates should be treated not as a set of isolated algorithms, but as an optimization problem whose mechanisms can be studied systematically and improved through transferable principles.

Nikita Vassilyev, William Berrios, Ruowang Zhang +3

Contextual AI

LLM Agent Self-ImprovementIn-Context Learning
AskPDF
Mar 28, 2026

GUIDE: Guided Updates for In-context Decision Evolution in LLM-Driven Spacecraft Operations

Large language models (LLMs) have been proposed as supervisory agents for spacecraft operations, but existing approaches rely on static prompting and do not improve across repeated executions. We introduce GUIDE, a non-parametric policy improvement framework that enables cross-episode adaptation without weight updates by evolving a structured, state-conditioned playbook of natural-language decision rules. A lightweight acting model performs real-time control, while offline reflection updates the playbook from prior trajectories. Evaluated on an adversarial orbital interception task in the Kerbal Space Program Differential Games environment, GUIDE's evolution consistently outperforms static baselines. Results indicate that context evolution in LLM agents functions as policy search over structured decision rules in real-time closed-loop spacecraft interaction.

Alejandro Carrasco, Mariko Storey-Matsutani, Victor Rodriguez-Fernandez +1

Massachusetts Institute of Technology Cambridge, USA · Universidad Politecnica de Madrid Madrid, Spain

Language Model-Based ControlLLM Agent Self-ImprovementIn-Context RL
AskPDF
Mar 26, 2026

Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills

Large Language Model (LLM) agents increasingly rely on domain-specific skills, yet manually authoring such skills does not scale, and skills generated purely from parametric knowledge often miss critical operational pitfalls. We introduce Trace2Skill, a framework that consolidates broad execution trajectories in parallel into a unified skill directory through inductive reasoning over agent experience. Trace2Skill supports both deepening existing human-written skills and creating useful skills from weak LLM-generated drafts. Experiments demonstrate the effectiveness of Trace2Skill across diverse domains, including office workflows, math reasoning, and vision QA. Importantly, the evolved skills are not merely memorized artifacts of the trajectories used to create them: they often transfer across model scales, across model families, and to out-of-distribution settings. For example, skills evolved from Qwen3.5-35B trajectories improve a Qwen3.5-122B agent by up to 57.6557.65 percentage points on WikiTableQuestions. Further analyses show that Trace2Skill outperforms sequential skill editing and ReasoningBank-style retrieval memories, compresses recurring failures and workarounds into standard operating procedures (SoPs), and yields portable skills that can be reused without parameter updates or test-time retrieval.

Jingwei Ni, Yihao Liu, Xinpeng Liu +7

ETH Zürich · University of Zurich · Peking University +2

LLM Agent Skill LearningLLM Agent Self-Improvement
AskPDF
Mar 25, 2026

AnalogAgent: Self-Improving Analog Circuit Design Automation with LLM Agents

Recent advances in large language models (LLMs) suggest strong potential for automating analog circuit design. Yet most LLM-based approaches rely on a single-model loop of generation, diagnosis, and correction, which favors succinct summaries over domain-specific insight and suffers from context attrition that erases critical technical details. To address these limitations, we propose AnalogAgent, a training-free agentic framework that integrates an LLM-based multi-agent system (MAS) with self-evolving memory (SEM) for analog circuit design automation. AnalogAgent coordinates a Code Generator, Design Optimizer, and Knowledge Curator to distill execution feedback into an adaptive playbook in SEM and retrieve targeted guidance for subsequent generation, enabling cross-task transfer without additional expert feedback, databases, or libraries. Across established benchmarks, AnalogAgent achieves 92% Pass@1 with Gemini and 97.4% Pass@1 with GPT-5. Moreover, with compact models (e.g., Qwen-8B), it yields a +48.8% average Pass@1 gain across tasks and reaches 72.1% Pass@1 overall, indicating that AnalogAgent substantially strengthens open-weight models for high-quality analog circuit design automation.

Zhixuan Bao, Zhuoyi Lin, Jiageng Wang +5

Nanyang Technological University Singapore · Institute for Infocomm Research Singapore · Institute of Microelectronics Singapore +2

Electronic Design AutomationLLM Agent Self-ImprovementMemory-Augmented Language Model AgentsMulti-Agent LLM Systems
AskPDF
Mar 21, 2026

REVERE: Reflective Evolving Research Engineer

Existing prompt-optimization techniques rely on local signals, causing poor generalization across tasks. In addition, they also rely on weak update mechanisms, such as full-prompt rewrites or unstructured merges, which cause knowledge loss and unstable adaptation. These limitations are magnified in research-coding workflows, which involve heterogeneous repositories and weak feedback, limiting abstraction and learning across tasks. We introduce Reflective Evolving Research Engineer (REVERE), a lightweight, self-adapting agent framework that learns from a Global Training Context, distills recurring cross-repository failure modes into reusable heuristics, and applies targeted, code-based edits to agent prompts. REVERE is evaluated across settings ranging from long-horizon to single-shot benchmarks, and improves over prior expert-crafted instructions by 4.50% on SUPER, 1.3% on ResearchCodeBench, and 4.89% on ScienceAgentBench. It does so at nearly 10x lower cost and 2.7x faster adaptation than existing prompt-optimization baselines, demonstrating that self-adapting agents with continual learning and global memory consolidation can meaningfully evolve their capabilities over time.

Balaji Dinesh Gangireddi, Aniketh Garikaparthi, Manasi Patwardhan +1

TCS Research · Yale University

LLM Agent Self-ImprovementPrompt OptimizationSoftware Engineering AgentsContinual Learning for LLM AgentsMemory-Augmented Agents
AskPDF
Mar 18, 2026

CentaurTA Studio: A Self-Improving Human-Agent Collaboration System for Thematic Analysis

Thematic analysis is difficult to scale: manual workflows are labor-intensive, while fully automated pipelines often lack controllability and transparent evaluation. We present CentaurTA Studio, a web-based system for self-improving human--agent collaboration in open coding and theme construction. The system integrates (1) a two-stage human feedback pipeline separating simulator drafting and expert validation, (2) persistent prompt optimization that distills validated feedback into reusable alignment principles, and (3) rubric-based evaluation with early stopping for process control. Across three domains, CentaurTA achieves the strongest performance in both Open Coding and Theme Construction, reaching up to 92.12% accuracy and consistently outperforming baseline systems. Agreement between the rubric-based LLM judge and human annotators reaches substantial reliability (average κ=0.68κ= 0.68). Ablation studies show that removing the feedback loop reduces performance from 90% to 81%, while eliminating the Critic or early stopping degrades accuracy or increases interaction cost. The full system reaches peak performance within 10 iterative rounds (about 25 minutes), demonstrating improved efficiency over expert-only refinement.

Lei Wang, Min Huang, Eduard Dragut

Temple University · Independent Researcher

Human-AI CollaborationLLM Agent Self-Improvement
AskPDF
Mar 16, 2026

OpenHospital: A Thing-in-itself Arena for Evolving and Benchmarking LLM-based Collective Intelligence

Large Language Model (LLM)-based Collective Intelligence (CI) presents a promising approach to overcoming the data wall and continuously boosting the capabilities of LLM agents. However, there is currently no dedicated arena for evolving and benchmarking LLM-based CI. To address this gap, we introduce OpenHospital, an interactive arena where physician agents can evolve CI through interactions with patient agents. This arena employs a data-in-agent-self paradigm that rapidly enhances agent capabilities and provides robust evaluation metrics for benchmarking both medical proficiency and system efficiency. Experiments demonstrate the effectiveness of OpenHospital in both fostering and quantifying CI.

Peigen Liu, Rui Ding, Yuren Mao +7

School of Software Technology, Zhejiang University · Laboratory for Statistical Monitoring and Intelligent Governance of Common Prosperity, Zhejiang Gongshang University · Tongyi Lab, Alibaba Group +1

LLM AgentsAI Agent BenchmarksLLM Agent Self-ImprovementLLM Agent Training
AskPDF
Mar 16, 2026

GameUIAgent: An LLM-Powered Framework for Automated Game UI Design with Structured Intermediate Representation

Game UI design requires consistent visual assets across rarity tiers yet remains a predominantly manual process. We present GameUIAgent, an LLM-powered agentic framework that translates natural language descriptions into editable Figma designs via a Design Spec JSON intermediate representation. A six-stage neuro-symbolic pipeline combines LLM generation, deterministic post-processing, and a Vision-Language Model (VLM)-guided Reflection Controller (RC) for iterative self-correction with guaranteed non-regressive quality. Evaluated across 110 test cases, three LLMs, and three UI templates, cross-model analysis establishes a game-domain failure taxonomy (rarity-dependent degradation; visual emptiness) and uncovers two key empirical findings. A Quality Ceiling Effect (Pearson r=-0.96, p<0.01) suggests that RC improvement is bounded by headroom below a quality threshold -- a visual-domain counterpart to test-time compute scaling laws. A Rendering-Evaluation Fidelity Principle reveals that partial rendering enhancements paradoxically degrade VLM evaluation by amplifying structural defects. Together, these results establish foundational principles for LLM-driven visual generation agents in game production.

Wei Zeng, Fengwei An, Zhen Liu +1

School of Microelectronics, Southern University of Science and Technology (SUSTech), Shenzhen, China · Zhongguancun Academy, Beijing, China · School of Marxism, Tsinghua University, Beijing, China

Vision-Language AgentsLLM Agent Self-Improvement
AskPDF
Mar 11, 2026

Trajectory-Informed Memory Generation for Self-Improving Agent Systems

LLM-powered agents face a persistent challenge: learning from their execution experiences to improve future performance. While agents can successfully complete many tasks, they often repeat inefficient patterns, fail to recover from similar errors, and miss opportunities to apply successful strategies from past executions. We present a novel framework for automatically extracting actionable learnings from agent execution trajectories and utilizing them to improve future performance through contextual memory retrieval. Our approach comprises four components: (1) a Trajectory Intelligence Extractor that performs semantic analysis of agent reasoning patterns, (2) a Decision Attribution Analyzer that identifies which decisions and reasoning steps led to failures, recoveries, or inefficiencies, (3) a Contextual Learning Generator that produces three types of guidance -- strategy tips from successful patterns, recovery tips from failure handling, and optimization tips from inefficient but successful executions, and (4) an Adaptive Memory Retrieval System that injects relevant learnings into agent prompts based on multi-dimensional similarity. Unlike existing memory systems that store generic conversational facts, our framework understands execution patterns, extracts structured learnings with provenance, and retrieves guidance tailored to specific task contexts. Evaluation on the AppWorld benchmark demonstrates consistent improvements, with up to 14.3 percentage point gains in scenario goal completion on held-out tasks and particularly strong benefits on complex tasks (28.5~pp scenario goal improvement, a 149% relative increase).

Gaodan Fang, Vatche Isahagian, K. R. Jayaram +4

Agents and Automation Lab, IBM Research USA

LLM Agent Self-ImprovementLLM Agent MemoryMemory-Augmented Language Model Agents
AskPDF
Mar 9, 2026

MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games

Multi-turn, multi-agent LLM game evaluations often exhibit substantial run-to-run variance. In long-horizon interactions, small early deviations compound across turns and are amplified by multi-agent coupling. This biases win rate estimates and makes rankings unreliable across repeated tournaments. Prompt choice worsens this further by producing different effective policies. We address both instability and underperformance with MEMO (Memory-augmented MOdel context optimization), a self-play framework that optimizes inference-time context by coupling retention and exploration. Retention maintains a persistent memory bank that stores structured insights from self-play trajectories and injects them as priors during later play. Exploration runs tournament-style prompt evolution with uncertainty-aware selection via TrueSkill, and uses prioritized replay to revisit rare and decisive states. Across five text-based games, MEMO raises mean win rate from 25.1% to 49.5% for GPT-4o-mini and from 20.9% to 44.3% for Qwen-2.5-7B-Instruct, using 2,0002,000 self-play games per task. Run-to-run variance also drops, giving more stable rankings across prompt variations. These results suggest that multi-agent LLM game performance and robustness have substantial room for improvement through context optimization. MEMO achieves the largest gains in negotiation and imperfect-information games, while RL remains more effective in perfect-information settings. All code is open-source and available here: https://github.com/openverse-ai/MEMO

Yunfei Xie, Kevin Wang, Bobby Cheng +9

Rice University · The University of Texas at Austin · A*STAR +3

Multi-Agent LLM SystemsLLM Agent Self-ImprovementGame-Playing AgentsMemory-Augmented Language Model AgentsPrompt Optimization
AskPDF
Mar 5, 2026

EvoTool: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection

LLM-based agents depend on effective tool-use policies to solve complex tasks, yet optimizing these policies remains challenging due to delayed supervision and the difficulty of credit assignment in long-horizon trajectories. Existing optimization approaches tend to be either monolithic, which are prone to entangling behaviors, or single-aspect, which ignore cross-module error propagation. To address these limitations, we propose EvoTool, a self-evolving framework that optimizes a modular tool-use policy via a gradient-free evolutionary paradigm. EvoTool decomposes agent's tool-use policy into four modules, including Planner, Selector, Caller, and Synthesizer, and iteratively improves them in a self-improving loop through three novel mechanisms. Trajectory-Grounded Blame Attribution uses diagnostic traces to localize failures to a specific module. Feedback-Guided Targeted Mutation then edits only that module via natural-language critique. Diversity-Aware Population Selection preserves complementary candidates to ensure solution diversity. Across four benchmarks, EvoTool outperforms strong baselines by over 5 points on both GPT-4.1 and Qwen3-8B, while achieving superior efficiency and transferability. The code will be released once paper is accepted.

Shuo Yang, Soyeon Caren Han, Xueqi Ma +3

School of Computing and Information Systems, The University of Melbourne

Policy OptimizationLLM Agent Self-ImprovementSelf-Evolving AgentsEvolutionary OptimizationRL for Tool Use
AskPDF