The Meta-Agent Challenge shows frontier AI models rarely match human-engineered agent baselines when tasked with autonomous development, with proprietary models succeeding most often and some exhibiting cheating under pressure.
hub Canonical reference
Memento-skills: Let agents design agents
Canonical reference. 89% of citing Pith papers cite this work as background.
24
Pith papers citing it
Background
89% of classified citations
hub tools
citation-role summary
background 8
method 1
citation-polarity summary
years
2026 24representative citing papers
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.
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.
Residual skill optimization creates complementary Text-to-SQL agents by training each new skill on prior ensemble failures, yielding accuracy gains on Spider2-Lite and transfer to other dialects and tasks.
OLIVIA treats LLM agent action selection as a contextual linear bandit over frozen hidden states and applies UCB exploration to adapt online, yielding consistent gains over static ReAct and prompt-based baselines on four 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.
SkillGuard extracts executable environment contracts from LLM skill documents to detect only relevant drifts, reporting zero false positives on 599 cases, 100% precision in known-drift tests, and raising one-round repair success from 10% to 78%.
CMIB uses a conditional multimodal information bottleneck to create reusable agent skills that separate verbalizable text content from predictive perceptual residuals, improving execution stability.
SkillRet benchmark shows fine-tuned retrievers improve NDCG@10 by 13+ points over prior models on large-scale skill retrieval for LLM agents.
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.
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.
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.
Introduces EvoArena benchmark for dynamic LLM agent environments and EvoMem memory paradigm that improves accuracy by 1.5% on EvoArena and gains on GAIA and LoCoMo.
Introduces VideoWeaver benchmark (16 categories, 285 cases) plus agent-as-judge and skill-evolution algorithm to assess and improve agentic long video generation across frameworks.
CASCADE enables LLMs to continually adapt at deployment via case-based episodic memory and contextual bandits, improving macro-averaged success by 20.9% over zero-shot on 16 tasks spanning medicine, law, code, and robotics.
Compact control-oriented strategy genes outperform documentation-heavy skill packages for test-time guidance and iterative experience evolution on scientific coding tasks.
OpenSkill bootstraps LLM agent self-evolution by pulling grounded knowledge and anchors from open-world sources, synthesizing transferable skills, and refining them on self-generated virtual tasks, achieving top benchmark pass rates without supervision.
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 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.
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.
Web2BigTable introduces a bi-level multi-agent system that achieves new state-of-the-art results on wide-coverage and deep web-to-table search benchmarks through orchestration, coordination, and closed-loop reflection.
Current agentic RL systems lack three key components needed for self-evolving agents at scale, requiring new co-designed architectures such as AReaL2.0 to enable policy updates from deployed workloads.
A survey that defines agent skills as reusable procedural artifacts and reviews methods, resources, and applications across their representation, acquisition, retrieval, and evolution stages.
citing papers explorer
-
The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?
The Meta-Agent Challenge shows frontier AI models rarely match human-engineered agent baselines when tasked with autonomous development, with proprietary models succeeding most often and some exhibiting cheating under pressure.
-
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.
-
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.
-
Residual Skill Optimization for Text-to-SQL Ensembles
Residual skill optimization creates complementary Text-to-SQL agents by training each new skill on prior ensemble failures, yielding accuracy gains on Spider2-Lite and transfer to other dialects and tasks.
-
OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents
OLIVIA treats LLM agent action selection as a contextual linear bandit over frozen hidden states and applies UCB exploration to adapt online, yielding consistent gains over static ReAct and prompt-based baselines on four 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.
-
Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries
SkillGuard extracts executable environment contracts from LLM skill documents to detect only relevant drifts, reporting zero false positives on 599 cases, 100% precision in known-drift tests, and raising one-round repair success from 10% to 78%.
-
Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck
CMIB uses a conditional multimodal information bottleneck to create reusable agent skills that separate verbalizable text content from predictive perceptual residuals, improving execution stability.
-
SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents
SkillRet benchmark shows fine-tuned retrievers improve NDCG@10 by 13+ points over prior models on large-scale skill retrieval for LLM agents.
-
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.
-
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.
-
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.
-
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
Introduces EvoArena benchmark for dynamic LLM agent environments and EvoMem memory paradigm that improves accuracy by 1.5% on EvoArena and gains on GAIA and LoCoMo.
-
VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation
Introduces VideoWeaver benchmark (16 categories, 285 cases) plus agent-as-judge and skill-evolution algorithm to assess and improve agentic long video generation across frameworks.
-
CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment
CASCADE enables LLMs to continually adapt at deployment via case-based episodic memory and contextual bandits, improving macro-averaged success by 20.9% over zero-shot on 16 tasks spanning medicine, law, code, and robotics.
-
From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution
Compact control-oriented strategy genes outperform documentation-heavy skill packages for test-time guidance and iterative experience evolution on scientific coding tasks.
-
OpenSkill: Open-World Self-Evolution for LLM Agents
OpenSkill bootstraps LLM agent self-evolution by pulling grounded knowledge and anchors from open-world sources, synthesizing transferable skills, and refining them on self-generated virtual tasks, achieving top benchmark pass rates without supervision.
-
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.
-
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.
-
Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction
Web2BigTable introduces a bi-level multi-agent system that achieves new state-of-the-art results on wide-coverage and deep web-to-table search benchmarks through orchestration, coordination, and closed-loop reflection.
-
Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents
Current agentic RL systems lack three key components needed for self-evolving agents at scale, requiring new co-designed architectures such as AReaL2.0 to enable policy updates from deployed workloads.
-
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.
- AgentPSO: Evolving Agent Reasoning Skill via Multi-agent Particle Swarm Optimization