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
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
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.
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%.
The paper surveys agent skills for LLM agents, organizing the literature into a four-stage lifecycle of representation, acquisition, retrieval, and evolution while highlighting their role in system scalability.
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.
-
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.
-
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.
-
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%.
-
A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
The paper surveys agent skills for LLM agents, organizing the literature into a four-stage lifecycle of representation, acquisition, retrieval, and evolution while highlighting their role in system scalability.