arXiv AI
Jul 14
Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries
arXiv:2607. 10113v1 Announce Type: new Abstract: Large language model agents increasingly store reusable procedures outside the model.
Skill Dreaming: Evolving Repository Skills through Pull Request Streams
Skill Dreaming is a framework that learns from pull request (PR) streams to build and continuously refine a repository‑specific skill library. By extracting executable knowledge from validated PRs, it guides LLM agents in implementing features, maintaining tests, documentation, and repository conventions. The framework integrates PR analysis, skill management, code execution, and continuous integration to create an end‑to‑end workflow that updates skills as new PRs arrive.
Related stories
Hugging Face Trending Papers
Jul 30
Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments
Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation. Each task must couple a realistic software state with a specification, development tools, and reliable verification.
arXiv Machine Learning
Jul 31
Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments
arXiv:2607. 28591v1 Announce Type: cross Abstract: Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation.
Hugging Face Trending Papers
Aug 19
SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
SkillForge is a self‑distillation framework that proactively builds project‑specific knowledge for large language model agents by synthesizing and resolving artificial issues derived from a repository’s test‑covered core functionalities. Rather than waiting for real issues to reveal knowledge gaps, SkillForge generates these synthetic problems, learns reusable entity‑grounded skills, and associates them with relevant repository entities. Experiments with both open‑source and closed‑source models show that this proactive knowledge acquisition consistently outperforms strong baselines in issue resolution tasks.
arXiv Computer Vision
Oct 9
Skill-V: Verifiable Self-Evolving Skill Library for Interactive Agents
Skill‑V is a verifiable self‑evolving skill library for interactive agents that represents skills as versioned, falsifiable contracts linking semantic intent to observable behavior. The system uses task failures to add new skills and contract‑outcome disagreements to revise existing skill boundaries, ensuring revisions preserve semantic constraints and pass non‑regression tests on historical evidence. An applicability‑aware filter excludes confidently inapplicable skill candidates, leading to high success rates on ALFWorld (95.3%) and WebShop (85.9%) while keeping the library more compact than growth‑only baselines.
arXiv AI
Jul 7
SkillFab: An Agent-Native Skill Production Platform
arXiv:2607. 03780v1 Announce Type: cross Abstract: SkillFab is an agent-native platform for turning missing capabilities into reviewed, reusable Agent Skills.
arXiv AI
Aug 20
SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
SkillForge is a self‑distillation framework that proactively builds project‑specific knowledge for large language model agents by synthesizing and resolving artificial issues derived from a repository’s test‑covered core functionalities. By distilling these solutions into entity‑grounded skills linked to repository entities, the system equips agents with reusable, project‑specific expertise before encountering real issues. Experiments with both open‑source and closed‑source models show that SkillForge consistently outperforms strong baselines in issue resolution tasks.
arXiv Machine Learning
Oct 28
Software Engineering LLMs: Why We Need Them and How Software Engineering Helps Build Them
The paper discusses how software engineering (SE) expertise can guide the training of large language models (LLMs) for coding tasks. Using a case study of a 92‑billion‑parameter LLM, the authors created RefactorForge, a pipeline that leverages SE knowledge and tools to generate verified training data from 306 Python repositories. Fine‑tuning the model on this data improved performance on several benchmarks, including RefactorBench and SWE‑Bench ProMax, and the gains extended to other coding‑agent harnesses.
arXiv AI
Jul 22
Skillware: A Software Ontology and Engineering Lifecycle for Persistent Behavioral Artifacts
arXiv:2607. 18970v1 Announce Type: cross Abstract: Agent Skills have become persistent behavioral artifacts across independent AI agent systems.
arXiv AI
Jun 3
Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward
arXiv:2602. 12430v4 Announce Type: replace-cross Abstract: The transition from monolithic language models to modular, skill-equipped agents marks a defining shift in how large language models (LLMs) are deployed in practice.
arXiv Computation and Language
Oct 27
Hierarchical Skill Evolution for Coding Agent
arXiv:2610.35616v1 Announce Type: new Abstract: Skills provide agents with reusable experience to guide future decisions without modifying the underlying model. However, coding trajectories are often...
arXiv AI
Jun 18
SWE-Future: Forecast-Conditioned Data Synthesis for Future-Oriented Software Engineering Agents
arXiv:2606. 18733v1 Announce Type: cross Abstract: Realistic coding-agent benchmarks often replay public GitHub issues and pull requests, making them vulnerable to overlap with model pretraining, fine-tuning, synthetic-data generation, or benchmark-driven model selection.