interactive-tasks

Tag

Cards List
#interactive-tasks

Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents

arXiv cs.CL · 2026-06-01 Cached

This paper proposes MASA, a framework that adapts skills to each LLM backbone without modifying weights, using hierarchical evolution and a model-conditioned rewriter, achieving gains of up to 25.8 points over baselines.

0 favorites 0 likes
#interactive-tasks

SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories

Hugging Face Daily Papers · 2026-05-31 Cached

SkillAdaptor is a training-free step-level skill adaptation framework with explicit failure attribution for LLM agents, improving performance on WebShop, PinchBench, and Claw-Eval.

0 favorites 0 likes
← Back to home

Submit Feedback