SkillVine: Agent Skill Evolution via Branching Exploration

arXiv:2609.32731 · cs.AI · Submitted 2026-09-26 · Read on arXiv

cs.AI

Submitted: 2026-09-26

Updated: 2026-09-26

Code: https://github.com/EvolvingLMMs-Lab/SkillOpt-Lite

Terminology

• Benchmark — 32× in this paper · explained in 2 episodes
• Accuracy — 12× in this paper · explained in 1 episode
• Agent Skills — 8× in this paper · explained in 1 episode
• Ablation — 6× in this paper · explained in 1 episode
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Self-Evolving Agents — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Adaptive-Granularity Branch Update — 2× in this paper
• Agentic System — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Large Language Model — 2× in this paper
• Monte Carlo Tree Search — 2× in this paper
• Procedural Knowledge — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Budget-Constrained Optimization — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMs
• SIMA 2: A Generalist Embodied Agent for Virtual Worlds
• Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• Go-Explore: a New Approach for Hard-Exploration Problems
• A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
• rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
• LiveMathematicianBench: A Live Benchmark for Research-Level Mathematical Reasoning with Proof Sketches
• From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
• Population Based Training of Neural Networks
• Tree Search for Language Model Agents
• The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
• Improve Mathematical Reasoning in Language Models by Automated Process Supervision
• Learning While Acting: A Skill-Enhanced Test-Time Co-Evolution Framework for Online Lifelong Learning Agents
• Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
• OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning
• SkillOS: Learning Skill Curation for Self-Evolving Agents
• Anything2Skill: Compiling External Knowledge into Reusable Skills for Agents
• SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
• More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection