Glite ARF introduces a verifier-driven three-role framework for parallel LLM coding agents, demonstrated by first- and second-place finishes in the BEA 2026 vocabulary-difficulty shared task across three languages with 29.9-35.9% RMSE reduction at ~$450 API cost.
hub Canonical reference
EvoSkill: Automated Skill Discovery for Multi-Agent Systems
Canonical reference. 80% of citing Pith papers cite this work as background.
40
Pith papers citing it
Background
80% of classified citations
abstract
Coding agents are increasingly used as general-purpose problem solvers, but their flexibility does not by itself confer the domain expertise needed for specialized tasks. Recent work addresses this through \textit{agent skills}: reusable workflows, and code, that augment agents with domain-specific capabilities. Most skills today are hand-crafted, and existing evolutionary approaches optimize low-level artifacts (e.g. prompts \& code) that are tightly coupled to specific models and tasks. We introduce \textbf{EvoSkill}, a self-evolving framework that automatically discovers and refines agent skills through iterative failure analysis. EvoSkill analyzes execution failures, proposes new skills or edits to existing ones, and materializes them into structured, reusable skill folders. A Pareto frontier of agent programs governs selection, retaining only skills that improve held-out validation performance while the underlying model remains frozen. We evaluate EvoSkill on two benchmarks: OfficeQA, a grounded reasoning benchmark over U.S.\ Treasury data, where it improves exact-match accuracy by \textbf{7.3\%} (60.6\% $\to$ 67.9\%); and SealQA, a search-augmented QA benchmark with noisy retrieval, where it yields a \textbf{12.1\%} gain (26.6\% $\to$ 38.7\%). We also investigate the zero-shot transfer capabilties of skills evolved on one task to the other; in particular: skills evolved from SealQA transfers zero-shot to BrowseComp, improving accuracy by \textbf{5.3\%} without modification demonstrating that skill-level optimization produces transferable capabilities beyond the training task.
hub tools
citation-role summary
background 13
baseline 1
other 1
citation-polarity summary
years
2026 40representative citing papers
SkillEvolBench is a new diagnostic benchmark that evaluates the transition from episodic experience to procedural skills in LLM agents using role-conditioned task families and frozen deployment tests.
MMSkills packages multimodal procedural knowledge into state-conditioned skills with text, state cards, and multi-view keyframes, generated from public trajectories via an agentic process and used at inference via branch-loaded inspection to improve visual agents on GUI and game benchmarks.
Evolving-RL jointly optimizes experience extraction and utilization in LLM agents via RL with separate evaluation signals, delivering up to 98.7% relative gains on out-of-distribution tasks in ALFWorld and Mind2Web.
Agentic-imodels evolves scikit-learn regressors via an autoresearch loop to jointly boost predictive performance and LLM-simulatability, improving downstream agentic data science tasks by up to 73% on the BLADE benchmark.
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.
SkillFoundry mines heterogeneous scientific resources into a self-evolving library of validated agent skills, with 71.1% novelty versus prior libraries and measurable gains on coding benchmarks plus two genomics tasks.
SkillCoach introduces self-evolving rubrics derived from rollouts to evaluate and supervise four process dimensions of agentic skill-use separately from outcome success.
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.
AFTER benchmark shows single refinement improves LLM agent performance by 3.7-6.7 points and multi-model procedural skills reach 73.1% cross-model accuracy on 382 tasks.
Contrastive success/failure evidence, replay-based patch validation, and topology-aware routing improve training-free skill self-evolution for LLM agents.
Persistent decision history plus role-separated redacted evaluation lets agents continually improve skills across sessions and outperform commercial deep-research and prior skill-evolution baselines.
SkillAdaptor introduces step-level failure attribution and targeted skill updates for LLM agents, yielding performance gains on WebShop, PinchBench, and Claw-Eval benchmarks.
Automatically optimizing agent skill files on a branching lakehouse improved held-out validation accuracy by 31.9% on 25 synthetic-but-trace-anchored tasks.
SkillRevise iteratively refines initial LLM-generated agent skills using execution traces to diagnose defects and apply repairs, raising success rates from 36.05% to 61.63% on SkillsBench across three benchmarks and five LLMs.
VESTA introduces dynamic tool creation for VLMs that outperforms static-tool and no-tool baselines on distribution fitting, time series, and astronomy tasks in the new DAWN benchmark.
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.
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.
OpenSkillEval dynamically builds task instances across five application domains to evaluate 30 open skills with over 600 tests, finding that skill use depends heavily on model and framework and that many popular skills do not beat base agents.
EvoLib improves black-box LLM test-time performance by maintaining an evolving, self-scored library of reusable skills and insights, without parameter updates or ground-truth feedback.
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.
citing papers explorer
-
Glite ARF: Verifier-Driven Research with Parallel LLM Coding Agents
Glite ARF introduces a verifier-driven three-role framework for parallel LLM coding agents, demonstrated by first- and second-place finishes in the BEA 2026 vocabulary-difficulty shared task across three languages with 29.9-35.9% RMSE reduction at ~$450 API cost.
-
SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills
SkillEvolBench is a new diagnostic benchmark that evaluates the transition from episodic experience to procedural skills in LLM agents using role-conditioned task families and frozen deployment tests.
-
MMSkills: Towards Multimodal Skills for General Visual Agents
MMSkills packages multimodal procedural knowledge into state-conditioned skills with text, state cards, and multi-view keyframes, generated from public trajectories via an agentic process and used at inference via branch-loaded inspection to improve visual agents on GUI and game benchmarks.
-
Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents
Evolving-RL jointly optimizes experience extraction and utilization in LLM agents via RL with separate evaluation signals, delivering up to 98.7% relative gains on out-of-distribution tasks in ALFWorld and Mind2Web.
-
Agentic-imodels: Evolving agentic interpretability tools via autoresearch
Agentic-imodels evolves scikit-learn regressors via an autoresearch loop to jointly boost predictive performance and LLM-simulatability, improving downstream agentic data science tasks by up to 73% on the BLADE benchmark.
-
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.
-
SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources
SkillFoundry mines heterogeneous scientific resources into a self-evolving library of validated agent skills, with 71.1% novelty versus prior libraries and measurable gains on coding benchmarks plus two genomics tasks.
-
SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use
SkillCoach introduces self-evolving rubrics derived from rollouts to evaluate and supervise four process dimensions of agentic skill-use separately from outcome success.
-
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.
-
Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation
AFTER benchmark shows single refinement improves LLM agent performance by 3.7-6.7 points and multi-model procedural skills reach 73.1% cross-model accuracy on 382 tasks.
-
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.
-
SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History
Persistent decision history plus role-separated redacted evaluation lets agents continually improve skills across sessions and outperform commercial deep-research and prior skill-evolution baselines.
-
SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
SkillAdaptor introduces step-level failure attribution and targeted skill updates for LLM agents, yielding performance gains on WebShop, PinchBench, and Claw-Eval benchmarks.
-
"Skill Issues'': Data-Centric Optimization of Lakehouse Agents
Automatically optimizing agent skill files on a branching lakehouse improved held-out validation accuracy by 31.9% on 25 synthetic-but-trace-anchored tasks.
-
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
SkillRevise iteratively refines initial LLM-generated agent skills using execution traces to diagnose defects and apply repairs, raising success rates from 36.05% to 61.63% on SkillsBench across three benchmarks and five LLMs.
-
VESTA: Visual Exploration with Statistical Tool Agents
VESTA introduces dynamic tool creation for VLMs that outperforms static-tool and no-tool baselines on distribution fitting, time series, and astronomy tasks in the new DAWN benchmark.
-
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.
-
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.
-
OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents
OpenSkillEval dynamically builds task instances across five application domains to evaluate 30 open skills with over 600 tests, finding that skill use depends heavily on model and framework and that many popular skills do not beat base agents.
-
Test-Time Learning with an Evolving Library
EvoLib improves black-box LLM test-time performance by maintaining an evolving, self-scored library of reusable skills and insights, without parameter updates or ground-truth feedback.
-
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.
-
SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents
SkillLens organizes skills into policies-strategies-procedures-primitives layers, retrieves via degree-corrected random walk, and uses a verifier for local adaptation, yielding up to 6.31 pp gains on MuLocbench and raising ALFWorld success from 45% to 51.31%.
-
From Context to Skills: Can Language Models Learn from Context Skillfully?
Ctx2Skill automatically produces natural-language skill files via self-play between a challenger, a reasoner, and a judge, improving LLM performance on context-learning 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%.
-
SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology
SkillGraph jointly evolves agent skills and collaboration topologies in multi-agent vision-language systems using a multimodal graph transformer and a skill designer, yielding consistent performance gains on benchmarks.
-
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
A skill-lifecycle agent (create, memory, manage, evaluate, refine) beats Hermes, Codex, and Claude Code on SkillsBench/SkillLearnBench and transfers skills better.
-
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.
-
Parametric Skills
ParametricSkills uses a hypernetwork to turn textual skills into LoRA adapters, outperforming in-context learning by 6.44 points on average across six SWE subtasks with higher BERT Score and F1.
-
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.
-
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.
-
Pomona: Continuous Code Quality Improvement via Small, Agentic Pull Requests at Bloomberg
A two-skill agentic tool (Pomona) that fixes code-quality issues via approximately 10-line pull requests saw 15 of 17 PRs merged in a one-month Bloomberg team pilot.
-
Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence
Safactory integrates three platforms for simulation, data management, and agent evolution to create a unified pipeline for training trustworthy autonomous AI.
-
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.
- SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering