Skip to content

Hierarchical Skill Evolution for Coding Agent

Oct 2026 · 0 citations · 20 references
Computer Science

TL;DR

HSE progressively distills procedural knowledge from coding trajectories through hierarchical evidence aggregation, which evolves the skill library from target-benchmark trajectories without verifier feedback, relying solely on the learned evaluator for candidate assessment and achieving additional gains through benchmark-tailored skills.

Abstract

Skills provide agents with reusable experience to guide future decisions without modifying the underlying model. However, coding trajectories are often entangled with task- and repository-specific contexts, making it challenging to distill procedural skills that generalize across diverse coding environments. To address this challenge, we present Hierarchical Skill Evolution (HSE), which progressively distills procedural knowledge from coding trajectories through hierarchical evidence aggregation. HSE first extracts task-level evidence from individual trajectories, then aggregates recurring evidence within the same repository to form repository-specific skill candidates, and finally consolidates consistent patterns across repositories into transferable skills across repositories. The evolution is driven by an external writer-evaluator loop that generates and assesses skills while keeping the underlying coding model frozen. The loop externally updates the writer and evaluator policies to improve subsequent skill generation and assessment. This hierarchy progressively filters task-specific details while preserving procedures that generalize across diverse coding environments. Successful trajectories yield reusable guidance for future tasks, while failed trajectories reveal recurring failure modes that guide avoidance and recovery. We evaluate HSE on SWE-bench Verified and DeepSWE, using GLM-5.2 across Pi and Claude Code harnesses and GPT-5.5 and Opus 4.8 with Pi. Across both benchmarks, 10 skills evolved solely from SWE-Gym improve coding performance across all evaluated settings, demonstrating transfer across benchmarks, coding models, and agent harnesses. We further evolve the skill library from target-benchmark trajectories without verifier feedback, relying solely on the learned evaluator for candidate assessment and achieving additional gains through benchmark-tailored skills.

View source

Similar papers

Preprint Oct 2026

From Trajectories to Differentiated Skills: Cognitive Differentiation for Self-Improving Agents

Cognitive Differentiation in Skill Evolution (CDSE), which evolves a unified skill through four functionally distinct yet coordinated components: Meta, Experience, Tool, and Script, is proposed and achieves the highest scores in all 36 settings.

Ye-Wei Zhao, De-Rong Xu, Wei Chen et al. · 0 citations

SkillFocus: Evolving Agent Skills via Capability Decomposition

Across four benchmarks spanning heterogeneous tasks, SkillFocus achieves the best held-out accuracy on all four, outperforming the strongest competing result by 5.7 points on average while using 24\% fewer evolution tokens on average than the closest iterative baseline.

Ning Wang, Z. Gong, Bing-Dong Li et al. · 0 citations
Preprint Nov 2026

Program-Aided Patchable Skill Evolution

Agent skills have emerged as an effective means of enabling LLM agents to solve complex, interactive tasks by encoding reusable knowledge without modifying model parameters. Recent approaches further improve skill adaptation by distilling reusable experience from agent execution trajectories and evolving skills based o...

Jia-Hao Wang, Yu-Qi Xiong, Qing Yang et al. · 0 citations
Preprint Oct 2026

Selm: Self-Evolving Library Management for Multi-Skill Agent Optimization

Large language model (LLM) agents increasingly use skills as a lightweight way to acquire task-specific knowledge. Recent work enables skills to evolve from task trajectories. However, these methods often lack systematic management of evolved skills, making it difficult for agents to reuse and accumulate skills across...

Meng-Xi Hu, Yuxuan Hu, Jinbo Su et al. · 0 citations
Preprint Oct 2026

Holding a Steady Course: Knowledge Evolution from Expertise and Lessons for Continual Agent Learning

Autonomous agents are increasingly deployed across sequences of related tasks, yet they often fail to retain and improve their knowledge over time. Existing approaches convert interaction trajectories into memories or reusable skills, but experience is not automatically reliable knowledge. Automatically collected skill...

Wenzhe Fan, Benjamin Steenhoek, Gaurav Mittal et al. · 0 citations

Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents

Textual skills enable large language model (LLM) based agents to accumulate reusable procedural knowledge without updating model parameters. Yet existing skill evolution remains largely confined to the text space: an optimizer must diagnose success and failure patterns, and revise skills solely from long execution traj...

Kai-Xin Zhang, Chang-Ming Li, Ying-Dong Shi et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.