arXiv Computation and Language
Hierarchical Skill Evolution for Coding Agent
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Jun 16
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
arXiv:2605. 18401v2 Announce Type: replace-cross Abstract: Long-horizon LLM agents generate traces that could become reusable experience, but raw trajectories are noisy, local, and hard to govern.
arXiv Computation and Language
Sep 24
SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving
arXiv:2609.27717v1 Announce Type: new Abstract: Human-written agent skills encode rich workflows for real-world problem solving, but are typically used as external inference-time instructions rather...
arXiv AI
Sep 28
CODESKILL: Learning Self-Evolving Skills for Coding Agents
CODESKILL is an LLM-based framework that learns to extract, evolve, and maintain procedural skills from coding-agent trajectories. It treats skill extraction and skill-bank management as a learnable policy trained with reinforcement learning, using a hybrid reward combining rubric-based skill quality and verifiable execution feedback. Experiments on EnvBench, SWE-Bench Verified, and Terminal-Bench 2 demonstrate that CODESKILL raises average pass rates by 11.03 over a no-skill baseline and by 5.10 over the strongest prompt-based or memory baseline while keeping a compact skill bank.
arXiv AI
Jun 2
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
arXiv:2606. 01139v1 Announce Type: new Abstract: Agent skills are procedural artifacts that enable LLM agents to execute workflows, verify constraints, and recover from failures.
arXiv AI
Aug 7
Learning Globally Reusable Skills for Coding Agents
arXiv:2608. 06153v1 Announce Type: cross Abstract: Automated skill evolution enables Large Language Model (LLM) agents to continuously improve without expensive retraining.
arXiv AI
Oct 9
Code Understanding is a Bottleneck for Coding Agents
The paper introduces CABRA, a synthetic benchmark that constructs coding tasks from scratch using call‑graph transformations and scales difficulty along four axes: function traversal, search, runtime resolution, and instruction following. Experiments with eight large language models and six coding agents on 6,840 CABRA tasks show that while LLM accuracy degrades with task size, agents maintain high performance by leveraging tools; larger tasks trigger more tool calls, and a separate study on SWE‑bench verifies that tool‑call counts better predict agent accuracy than lines of code edited. The authors argue that CABRA exposes weaknesses in LLMs that are hidden by tool use and highlights the importance of code‑understanding abilities beyond mere editing. whyItMatters":"The study demonstrates that coding agents’ performance is more dependent on code‑understanding than on the amount of code edited, revealing a critical bottleneck for current coding agents."