Ctx2Skill lets language models autonomously evolve context-specific skills via multi-agent self-play, improving performance on context learning tasks without human supervision.
AutoRefine: From trajectories to reusable expertise for continual LLM agent refinement
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
years
2026 8roles
background 3polarities
background 3representative citing papers
EvoLib enables LLMs to accumulate, reuse, and evolve knowledge abstractions from inference trajectories at test time, yielding substantial gains on math reasoning, code generation, and agentic benchmarks without parameter updates or supervision.
This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
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.
PDI-guided distillation from environment-verified trajectories yields skills that surpass no-skill baselines and human-written skills across 86 tasks with far lower inference cost.
A survey that taxonomizes agent skills for LLM-based agents across representation, acquisition, retrieval, and evolution stages while reviewing methods, resources, and open challenges.
Compact Gene representations of experience outperform documentation-oriented Skill packages for test-time control and iterative evolution in code-solving tasks, with measured gains on CritPt from 9.1% to 18.57% and 17.7% to 27.14%.
citing papers explorer
-
From Context to Skills: Can Language Models Learn from Context Skillfully?
Ctx2Skill lets language models autonomously evolve context-specific skills via multi-agent self-play, improving performance on context learning tasks without human supervision.
-
Test-Time Learning with an Evolving Library
EvoLib enables LLMs to accumulate, reuse, and evolve knowledge abstractions from inference trajectories at test time, yielding substantial gains on math reasoning, code generation, and agentic benchmarks without parameter updates or supervision.
-
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
-
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.
-
Evidence Over Plans: Online Trajectory Verification for Skill Distillation
PDI-guided distillation from environment-verified trajectories yields skills that surpass no-skill baselines and human-written skills across 86 tasks with far lower inference cost.
-
A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
A survey that taxonomizes agent skills for LLM-based agents across representation, acquisition, retrieval, and evolution stages while reviewing methods, resources, and open challenges.
-
From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution
Compact Gene representations of experience outperform documentation-oriented Skill packages for test-time control and iterative evolution in code-solving tasks, with measured gains on CritPt from 9.1% to 18.57% and 17.7% to 27.14%.
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills