Branch2Skill: Efficient Skill Evolution Through Reasoning Trees

arXiv:2608.08677 · cs.AI · Submitted 2026-08-09 · Read on arXiv

Yanwei Ren, Haotian Zhang, Likang Xiao, Jiaxing Huang, Jiayan Qiu, Baosheng Yu, Quan Chen, Liu Liu

cs.AI

Submitted: 2026-08-09

Updated: 2026-08-11

Comments: 9 pages, 6 figures, 3 tables. Technical report

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

Terminology

• Benchmark — 18× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Papers — 3× in this paper · explained in 3 episodes
• Cross-Dataset Transfer — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Ablation Study — 1× in this paper · explained in 3 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 3 episodes
• Augmentation — 1× in this paper · explained in 2 episodes
• Cross-Model Transfer — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Frozen model — 1× in this paper · explained in 3 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Monte Carlo Tree Search (MCTS) — 1× in this paper · explained in 3 episodes
• Multi-Agent System — 1× in this paper · explained in 7 episodes
• Redundancy — 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
• SkillCAT: Contrastive, Assessment-Augmented and Topology-AwareSkill Self-Evolution for LLM Agents
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
• Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning
• LiveMathematicianBench: A Live Benchmark for Research-Level Mathematical Reasoning with Proof Sketches
• OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models
• 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
• SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
• ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• SkillGrad: Optimizing Agent Skills Like Gradient Descent
• SkillOpt: Executive Strategy for Self-Evolving Agent Skills
• SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories

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
• Agents' Last Exam
• 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