EvoAgentBench is a multi-domain benchmark for agent self-evolution that guarantees train-side ability support for every test task, revealing that curated skills transfer reliably but automatic methods remain brittle.
hub Canonical reference
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Canonical reference. 89% of citing Pith papers cite this work as background.
44
Pith papers citing it
Background
89% of classified citations
abstract
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 $57.65$ 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.
hub tools
citation-role summary
background 9
citation-polarity summary
years
2026 44roles
background 8representative citing papers
SkeMex distills agent trajectories into value-aware skills organized in general/task/action branches and evolves them via a closed-loop Read-Write-Assess-Govern process, outperforming prior memory agents on clinical tasks.
Framework estimates context-dependent marginal utility of candidate skills via reward gaps in matched base vs. skill-augmented rollouts to filter skills and co-train policy as generator.
SelSkill applies dual-granularity preference learning to selective skill-or-skip decisions, improving task success by 10.9 points and execution precision by 29.1 points on ALFWorld with Qwen3-8B.
DataPRM is an environment-aware generative process reward model that improves LLM data analysis agents by 7-11% on benchmarks via active verification and reflection-aware ternary rewards.
SkillFlow benchmark shows lifelong skill evolution yields modest gains for some models like Claude Opus 4.6 but limited or negative utility for others despite high skill usage.
TraceProbe normalizes coding agent trajectories into canonical actions and applies rule-based detectors to localize failure patterns and behavioral divergences that resolve rate hides.
CAD-IR scaffolds ambiguous text into executable CATIA procedures and, with expert-distilled skills, produces editable B-Rep variants of complex automotive parts.
COMFYCLAW introduces skill evolution via graph editing, automatic reversion, VLM verification, and distillation of runs into reusable Agent Skills, achieving higher average scores than a verifier-only baseline across benchmarks.
High-velocity agentic coding becomes governable when engineers convert recurring structural failures into durable, machine-actionable governance mechanisms rather than relying on continuous human code review.
SoftSkill compresses agent skills into length-32 continuous prefixes via next-token training of soft deltas, yielding 5.2-12.5 point gains over SkillOpt on SearchQA and LiveMath while using far fewer tokens.
Skill-MAS evolves a meta-skill for LLM-based multi-agent system generation via multi-trajectory rollout and selective reflection to improve performance without parametric updates.
Contrastive success/failure evidence, replay-based patch validation, and topology-aware routing improve training-free skill self-evolution for LLM agents.
W2S framework with RWSA decomposition converts heterogeneous traces into Skills and improves behavioral replay consistency by 10.5% over summarization baselines on 70 Skills.
Catalogs ten patterns and synthesizes a four-layer reference architecture for skill harnessing in LLM agents, evaluated via cross-instantiation on eight systems.
OptSkills clusters optimization problems by archetypes, distills workflow skills from successful trajectories, and achieves 68.27% micro-averaged accuracy on diverse benchmarks while outperforming DeepSeek-V3.2-Thinking by 4.53% on MIPLIB-NL.
SkillBrew introduces a Pareto-aware multi-objective optimization framework with bi-level propose-then-verify to curate skill banks for LLM agents, evaluated on two public benchmarks.
SGSD retrieves skill-mistake pairs to build a multi-teacher pool, validates teacher polarity via a verifier, and applies a gated objective to distill useful signals, yielding 6.2% average gains over GRPO on math benchmarks with Qwen3-1.7B.
SkillOpt introduces a controllable text-space optimizer that evolves agent skills via add/delete/replace edits accepted only on strict held-out validation improvement, reporting consistent gains across 52 model-benchmark-harness combinations.
A systematic study across five domains finds model-generated skills yield average gains but non-uniform negative transfer, with a meta-skill improving extraction quality.
A governance recipe—retire under-performing skills, cap the active set, and impose a meta-skill authoring style—raises held-out MBPP+ hard-100 pass@1 from 0.258 to 0.584, though the ungoverned 'drift' baseline itself is never run.
GraphMind builds and evolves action-centric workflow graphs from traces, navigates them via multi-agent LLM reasoning, and adapts via ATR, outperforming baselines on 93 incidents with 8x less context and 26% lower hallucination in production deployment.
A meta-skill authors and refines prose-and-code skills for agents by learning from post-deployment failures with an overfit audit, achieving 56.8% accuracy on SkillsBench tasks versus 43.6% for human-curated skills.
SkillRAE organizes skills into a graph and compiles compact, grounded contexts for LLM agents, yielding 11.7% gains on SkillsBench over prior RAE methods.
citing papers explorer
-
EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer
EvoAgentBench is a multi-domain benchmark for agent self-evolution that guarantees train-side ability support for every test task, revealing that curated skills transfer reliably but automatic methods remain brittle.
-
Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory
SkeMex distills agent trajectories into value-aware skills organized in general/task/action branches and evolves them via a closed-loop Read-Write-Assess-Govern process, outperforming prior memory agents on clinical tasks.
-
Co-Evolving Skill Generation and Policy Optimization
Framework estimates context-dependent marginal utility of candidate skills via reward gaps in matched base vs. skill-augmented rollouts to filter skills and co-train policy as generator.
-
Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning
SelSkill applies dual-granularity preference learning to selective skill-or-skip decisions, improving task success by 10.9 points and execution precision by 29.1 points on ALFWorld with Qwen3-8B.
-
Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis
DataPRM is an environment-aware generative process reward model that improves LLM data analysis agents by 7-11% on benchmarks via active verification and reflection-aware ternary rewards.
-
SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents
SkillFlow benchmark shows lifelong skill evolution yields modest gains for some models like Claude Opus 4.6 but limited or negative utility for others despite high skill usage.
-
What Resolve Rate Hides: Trajectory Structure Diagnostics for Coding Agents
TraceProbe normalizes coding agent trajectories into canonical actions and applies rule-based detectors to localize failure patterns and behavioral divergences that resolve rate hides.
-
ArtisanCAD: An Industrial-Level CAD Agent with Expert-Grounded Knowledge Distillation
CAD-IR scaffolds ambiguous text into executable CATIA procedures and, with expert-distilled skills, produces editable B-Rep variants of complex automotive parts.
-
COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows
COMFYCLAW introduces skill evolution via graph editing, automatic reversion, VLM verification, and distillation of runs into reusable Agent Skills, achieving higher average scores than a verifier-only baseline across benchmarks.
-
Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering
High-velocity agentic coding becomes governable when engineers convert recurring structural failures into durable, machine-actionable governance mechanisms rather than relying on continuous human code review.
-
SoftSkill: Behavioral Compression for Contextual Adaptation
SoftSkill compresses agent skills into length-32 continuous prefixes via next-token training of soft deltas, yielding 5.2-12.5 point gains over SkillOpt on SearchQA and LiveMath while using far fewer tokens.
-
Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems
Skill-MAS evolves a meta-skill for LLM-based multi-agent system generation via multi-trajectory rollout and selective reflection to improve performance without parametric updates.
-
SkillCAT: Contrastive, Assessment-Augmented and Topology-AwareSkill Self-Evolution for LLM Agents
Contrastive success/failure evidence, replay-based patch validation, and topology-aware routing improve training-free skill self-evolution for LLM agents.
-
Workflow-to-Skill: Skill Creation via Routing-Workflow-Semantics-Attachments Decomposition
W2S framework with RWSA decomposition converts heterogeneous traces into Skills and improves behavioral replay consistency by 10.5% over summarization baselines on 70 Skills.
-
Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agents
Catalogs ten patterns and synthesizes a four-layer reference architecture for skill harnessing in LLM agents, evaluated via cross-instantiation on eight systems.
-
OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation
OptSkills clusters optimization problems by archetypes, distills workflow skills from successful trajectories, and achieves 68.27% micro-averaged accuracy on diverse benchmarks while outperforming DeepSeek-V3.2-Thinking by 4.53% on MIPLIB-NL.
-
SkillBrew: Multi-Objective Curation of Skill Banks for LLM Agents
SkillBrew introduces a Pareto-aware multi-objective optimization framework with bi-level propose-then-verify to curate skill banks for LLM agents, evaluated on two public benchmarks.
-
Skill-Conditioned Gated Self-Distillation for LLM Reasoning
SGSD retrieves skill-mistake pairs to build a multi-teacher pool, validates teacher polarity via a verifier, and applies a gated objective to distill useful signals, yielding 6.2% average gains over GRPO on math benchmarks with Qwen3-1.7B.
-
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
SkillOpt introduces a controllable text-space optimizer that evolves agent skills via add/delete/replace edits accepted only on strict held-out validation improvement, reporting consistent gains across 52 model-benchmark-harness combinations.
-
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
A systematic study across five domains finds model-generated skills yield average gains but non-uniform negative transfer, with a meta-skill improving extraction quality.
-
Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries
A governance recipe—retire under-performing skills, cap the active set, and impose a meta-skill authoring style—raises held-out MBPP+ hard-100 pass@1 from 0.258 to 0.584, though the ungoverned 'drift' baseline itself is never run.
-
GraphMind: From Operational Traces to Self-Evolving Workflow Automation
GraphMind builds and evolves action-centric workflow graphs from traces, navigates them via multi-agent LLM reasoning, and adapts via ATR, outperforming baselines on 93 incidents with 8x less context and 26% lower hallucination in production deployment.
-
SkillEvolver: Skill Learning as a Meta-Skill
A meta-skill authors and refines prose-and-code skills for agents by learning from post-deployment failures with an overfit audit, achieving 56.8% accuracy on SkillsBench tasks versus 43.6% for human-curated skills.
-
SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Execution
SkillRAE organizes skills into a graph and compiles compact, grounded contexts for LLM agents, yielding 11.7% gains on SkillsBench over prior RAE methods.
-
Evidence Over Plans: Online Trajectory Verification for Skill Distillation
SPARK generates environment-verified trajectories to compute PDI, enabling posterior skill distillation that outperforms no-skill baselines and human-written skills across 86 tasks with up to 1000x cheaper inference.
-
SkillGen: Verified Inference-Time Agent Skill Synthesis
SkillGen synthesizes auditable skills from agent trajectories via contrastive induction on successes and failures, then verifies net performance impact by comparing outcomes with and without the skill on identical tasks.
-
ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillation
ClawTrace enables cost-aware LLM agent skill distillation by tracing per-step costs and generating preserve, prune, and repair patches, with ablations showing reduced regressions and prune rules transferring to cut costs by 32%.
-
Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents
Memory, skills, and rules in LLM agents sit on one compression spectrum, and no system yet supports adaptive cross-level compression.
-
SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skills
SkillDisCo distills reusable PFSM subgraphs from successful agent traces and compiles them into callable procedural skills, improving success rates and reducing turns on ALFWorld and WebArena.
-
Marginal Advantage Accumulation for Memory-Driven Agent Self-Evolution
MAA formalizes alignability and comparability conditions and uses differential signals, EMA accumulation, and semantic identity merging to enable cross-batch operation-level evidence accumulation, outperforming batch-level baselines in 14 of 16 settings while matching online methods.
-
EvoRec: Self Evolving Agentic Recommender Systems
EvoRec deploys four collaborating LLM agents that co-evolve recommendation models and their optimization methods, reporting up to 5.54% offline gains and 1.85% revenue lift in an online A/B test.
-
Unsupervised Skill Discovery for Agentic Data Analysis
DataCOPE uses verifier-guided contrastive distillation from agent trajectories to discover skills, yielding average gains of 9.71% on report-style and 32.30% on reasoning-style data analysis tasks across four model settings.
-
SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems
SkillSmith introduces a synergy-aware skill-tool co-evolution framework with atomic bundles, Lotka-Volterra-inspired interaction modeling, and anti-pattern recording that outperforms baselines on complex tasks.
-
Workflow Closure Is Not Scientific Closure in Auto-Research Systems
Survey of auto-research systems identifies objective, validation, and acceptance collapses, concluding that workflow closure does not equal scientific closure and advocating non-autonomous epistemic control.
-
Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents
Insights Generator is a multi-agent system that produces evidence-backed insights from corpora of LLM agent traces and yields 30.4pp performance gains when humans apply the reports.
-
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
SkillsVote is a governance system for agent skills that profiles corpora, recommends via search, and gates updates on successful reusable outcomes, yielding benchmark gains without model changes.
-
Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents
Retrieving similar past trajectories and synthesizing a task-conditioned skill prompt improves fixed LLM agents over static-skill and memory baselines on three benchmarks.
-
Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning
SLIM dynamically optimizes the active external skill set in agentic RL via leave-one-skill-out marginal contribution estimates and lifecycle operations, delivering a 7.1% average gain over baselines on ALFWorld and SearchQA while showing some skills remain externally useful.
-
Ace-Skill: Bootstrapping Multimodal Agents with Prioritized and Clustered Evolution
Ace-Skill boosts multimodal agent self-evolution via prioritized rollouts with lazy-decay tracking and semantic knowledge clustering, yielding up to 35% relative gains on tool-use benchmarks and zero-shot transfer to smaller models.
-
From Multi-Agent to Single-Agent: When Is Skill Distillation Beneficial?
A metric's 'freedom'—how weakly behavior variation couples to score variation—is claimed to predict skill-distillation benefit, but the proof and validation are flawed.
-
Agent Skill Evaluation and Evolution: Frameworks and Benchmarks
The paper surveys skill evolution frameworks in agentic systems, grouping them into execution feedback, trajectory distillation, compression, and reinforcement learning paradigms while analyzing gaps across six benchmark categories.
-
A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
A survey that defines agent skills as reusable procedural artifacts and reviews methods, resources, and applications across their representation, acquisition, retrieval, and evolution stages.
- The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents
- Ratchet: How Reliable Must an LLM Judge Be to Retire a Skill?