arXiv AI September 28, 2026 By Bart{\l}omiej Cupia{\l}, Jens Tuyls, Maciej Wo{\l}czyk, Davide Paglieri, Martin Klissarov, Benjamin Eysenbach, Piotr Mi{\l}o\'s, Karthik R. Narasimhan

Up and Down the Abstraction Ladder: Code-Based Skills for Language Agents

Read the original on arXiv AI →

The paper introduces CodeHack, a library of code-based skills with natural-language descriptions designed to improve language agents in complex environments like NetHack. By allowing agents to invoke reusable skills instead of selecting individual actions, the study shows that skill-based agents nearly triple game progression and cut inference cost by 86% in zero‑shot settings, while still retaining the option to fall back on primitive actions. In reinforcement learning, skill-based agents learn faster, achieving a 7.2× larger average gain in dungeon level within the same training budget.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

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...

By Zhilong Ge, Yuting Shao, Yutao Yang, Yuxuan Cai, Jie Zhou, Kai Chen, Bo Zhang, Qin Chen, Liang He

llms agents reinforcement-learning fine-tuning

arXiv AI

Sep 16

Coaching Qwen3 Coder 30B to Think Like a CodeClash Arena Agent

arXiv:2609.16096v1 Announce Type: cross Abstract: Large language model coding agents have recently become useful for software tasks, but weaker or open-weight agents still struggle to reliably interp...

By Ivy Ning Zhang

llms agents fine-tuning benchmarks

Hugging Face Trending Papers

Aug 11

SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models

Agent skills represent a standardized format for packaging procedural knowledge and domain expertise, serving within agent harness systems as an essential mechanism to continually constrain a language model's behavior space for repeatable, high-quality task execution. However, because strong closed-source models entail high inference costs, current popular agent harnesses, such as Codex and OpenClaw, remain prohibitively expensive when deploying these skills to accomplish real-world tasks.

llms agents reinforcement-learning benchmarks

arXiv AI

Aug 12

SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models

arXiv:2608. 10538v1 Announce Type: new Abstract: Agent skills represent a standardized format for packaging procedural knowledge and domain expertise, serving within agent harness systems as an essential mechanism to continually constrain a language model's behavior space for repeatable, high-quality task execution.

By Chenhao Dang, Siyuan Xiong, Conghui He, Weijia Li

llms agents reinforcement-learning benchmarks

Hugging Face Trending Papers

Sep 14

Coaching Qwen3 Coder 30B to Think Like a CodeClash Arena Agent

Large language model coding agents have recently become useful for software tasks, but weaker or open-weight agents still struggle to reliably interpret user intent and execute complex multi-step work...

llms agents fine-tuning benchmarks

arXiv AI

Sep 21

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

arXiv:2609.22068v1 Announce Type: new Abstract: Training capable coding agents via reinforcement learning (RL) requires diverse tasks with reliable verifiers. Open-source codebases offer a rich sourc...

By Bowen Ye, Lei Li, Shicheng Li, Zihao Yue, Linghao Zhang, Hanglong Lv, Yuanxin Liu, Wenhan Ma, Hao Tian, Rang Li, Jinhao Dong, Yikai Zhao, Xiangwei Deng, Hailin Zhang, Liang Zhao, Qi Liu, Lingpeng Kong, Tong Yang, Fuli Luo

agents reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving

Coaching Qwen3 Coder 30B to Think Like a CodeClash Arena Agent

SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models

SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models

Coaching Qwen3 Coder 30B to Think Like a CodeClash Arena Agent

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself