Self-Supervised Skill Optimization

arXiv:2607.28777 · cs.CL · Submitted 2026-07-30 · Read on arXiv

Siran Peng, Cuiyu Yang, Tianyu Fu, Tianshuo Zhang, Haoyuan Zhang, Weisong Zhao, Anyang Su, Minghui Wu, Huiying Li, Xiangyu Zhu, Chenxu Zhao, Zhen Lei

cs.CL

Submitted: 2026-07-30

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 18× in this paper · explained in 2 episodes
• LLM judge — 10× in this paper · explained in 2 episodes
• Clustering — 7× in this paper · explained in 2 episodes
• Self-Supervised Skill Optimization — 7× in this paper
• Ablation — 5× in this paper · explained in 1 episode
• Harness — 4× in this paper · explained in 2 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Large Language Model (LLM) — 3× in this paper · explained in 3 episodes
• Pairwise Comparisons — 3× in this paper · explained in 2 episodes
• Context Memory — 2× in this paper
• Generator — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Chain-of-Thought (CoT) — 1× in this paper · explained in 5 episodes
• Content Rephrasing — 1× in this paper
• Distillation — 1× in this paper · explained in 2 episodes
• GRPO — 1× in this paper · explained in 6 episodes
• Iterative Refinement — 1× in this paper · explained in 5 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 4 episodes
• Meeting of the Association for Computational Linguistics — 1× in this paper
• Position Bias — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• EvoSkill: Automated Skill Discovery for Multi-Agent Systems
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• SelfEvoSkill: Paired Execution Audits for Skill Revision without External Outcome Supervision
• SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinement
• LiveMathematicianBench: A Live Benchmark for Research-Level Mathematical Reasoning with Proof Sketches
• SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
• SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support
• SkillGen: Verified Inference-Time Agent Skill Synthesis
• Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
• OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning
• UPA: Unsupervised Prompt Agent via Tree-Based Search and Selection
• AutoRefine: Compiling Trajectories into Validated Typed Agent Artifacts
• Unsupervised Skill Discovery for Agentic Data Analysis
• Hypothesis-Driven Skill Optimization for LLM Agents
• SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources
• From Context to Skills: Can Language Models Learn from Context Skillfully?
• Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO
• Self-Supervised Prompt Optimization
• OpenSkill: Open-World Self-Evolution for LLM Agents

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering