SkillRevise is an execution-grounded framework that iteratively refines initial, imperfect LLM agent skills by diagnosing defects from execution evidence and applying empirically validated edits, sign…

COLLEAGUE.SKILL introduces an automated system that distills heterogeneous traces of human expertise and role-specific knowledge into portable, inspectable, and usable AI skill packages.

SkillAdaptor is a novel, training-free framework that enables stable, step-level adaptation of external skills for LLM agents by precisely attributing failures to specific skills.

The paper proposes Skill-RM, a unified framework that treats reward modeling as an agentic task to consistently integrate diverse evaluation criteria, achieving superior performance over traditional m…

SkillsInjector proposes a two-stage adaptive method to dynamically optimize skill selection, quantity, and presentation for LLM agents, significantly improving task performance over static injection m…

SkillPager is a novel two-stage framework that efficiently selects minimal, execution-sufficient context from large procedural skill documents by leveraging typed semantic nodes, significantly reducin…

The paper introduces a data-centric optimization pipeline to improve coding agents' ability to interact with a branching lakehouse, showing significant accuracy gains by treating agent evaluation as a…

The paper introduces MASA, a model-aware skill alignment framework that adaptively rewrites general and task-specific skills for LLM agents, achieving superior performance across diverse backbones and…

The paper introduces TASTE, an automatic task synthesis method that generates challenging agent benchmarks by evolving tool sequences, demonstrating that existing benchmarks are saturated and that TAS…

SelSkill introduces a dual-granularity preference learning framework that treats skill use as a 'skill-or-skip' decision, significantly improving agent performance and execution precision in complex a…

This paper presents the first systematic study of black-box skill stealing attacks against proprietary LLM agents, demonstrating that structured agent skills can be easily extracted, posing a signific…

This paper empirically demonstrates that the choice of plan representation (e.g., checklist vs. narrative) significantly impacts the robustness and success rate of LLM-based web agents.

The paper proposes a modular agent framework and novel learning methods to design and optimize practical, cost-effective, and controllable LLM-based agentic systems.

SkillSmith is a synergy-aware framework that jointly co-evolves skills and tools, significantly improving self-improving agent systems by modeling skill-tool interactions and diagnosing failures.

The paper introduces MMG2Skill, a closed-loop framework that converts noisy, human-oriented web guides into editable, executable skills, significantly improving agent performance across diverse tasks.

The paper introduces Autonomous Agentic Data Engineering, demonstrating that LLMs can autonomously plan and optimize end-to-end data curation pipelines, leading to substantial performance gains in spe…

OptSkills introduces an archetype-centric skill learning agent that improves the generalization of solving optimization problems from natural language by clustering problems by underlying archetypes a…

The paper introduces Plan, a structured agentic behavior that decomposes multi-hop questions into ordered sub-questions before retrieval, and proposes a self-bootstrapping paradigm to train it without…

GRASP introduces a gated, regression-aware framework for improving LLM agents by ensuring that every proposed skill edit improves performance on a balanced probe without degrading previously learned c…