arXiv AI October 23, 2026 By Zijian Jiang, Xilu Wang

Robust Soft Skill Adaptation via Behavioral Localization in Tool-Using Agents

The paper introduces Behavioral Localization, a method that identifies a small subset of trajectory positions where a text skill most effectively improves a tool‑using agent’s performance. By comparing the agent’s behavior with and without the skill, the approach pinpoints positions that increase successful token likelihood and meaningfully alter the next token distribution. Using these localized positions to supervise a short soft prompt, the authors achieve significant performance gains on SpreadsheetBench, outperforming full‑trajectory supervision and on‑policy baselines.

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.

agents

arXiv AI

Jun 19

SoftSkill: Behavioral Compression for Contextual Adaptation

arXiv:2606. 20333v1 Announce Type: new Abstract: Agent skills are commonly deployed as natural-language Markdown files that encode answer policies, evidence-use habits, and task procedures.

By Xijia Tao, Yihua Teng, Xinyu Fu, Ziru Liu, Kecheng Chen, Yuzhi Zhao, Suiyun Zhang, Rui Liu, Lingpeng Kong

llms agents

arXiv AI

Jun 16

Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents

arXiv:2606. 16769v1 Announce Type: new Abstract: Agent skills are commonly distributed as SKILL.

By Tianyi Zhang, Zhonghao Qi

llms agents fine-tuning safety

arXiv AI

Oct 1

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

Rep2Skill introduces a representation-guided framework that enables large language model agents to self-evolve their textual skills by analyzing internal representation trajectories from agent rollouts. The method identifies execution turns that deviate from successful dynamics and uses these signals, together with execution contexts, as actionable feedback for targeted skill revision. Experiments with two open-source LLMs across two agent environments demonstrate that Rep2Skill consistently outperforms purely text-based approaches, showing that incorporating internal representations can enhance agent self-improvement.

By Kaixing Zhang, Changming Li, Yingdong Shi, Zheng Zhang, Kaitao Song, Wenjie Shi, Jingang Wang, Kan Ren

llms agents

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 1

WebXSkill: Skill Learning for Autonomous Web Agents

arXiv:2604.13318v2 Announce Type: replace Abstract: Autonomous web agents powered by large language models (LLMs) remain brittle on long-horizon browser workflows. A key bottleneck is a grounding gap...

By Zhaoyang Wang, Qianhui Wu, Xuchao Zhang, Chaoyun Zhang, Wenlin Yao, Fazle Elahi Faisal, Baolin Peng, Si Qin, Suman Nath, Qingwei Lin, Chetan Bansal, Dongmei Zhang, Saravan Rajmohan, Jianfeng Gao, Huaxiu Yao

llms agents

arXiv AI

Jun 30

SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models

arXiv:2601. 03555v3 Announce Type: replace Abstract: Training reliable tool-augmented agents remains a significant challenge, largely due to the difficulty of credit assignment in multi-step reasoning.

By Yuxuan Jiang, Francis Ferraro

llms agents reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

SoftSkill: Behavioral Compression for Contextual Adaptation

Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents

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

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

WebXSkill: Skill Learning for Autonomous Web Agents

SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models