skill-generation

Tag

Cards List
#skill-generation

Progressive Agent Skill Generation via Reinforcement Learning

Hugging Face Daily Papers · 2026-08-03 Cached

Introduces Skill-α, a reinforcement learning method for progressively generating high-quality agent skills by treating skill generation as sequential editing with a rollback reward. It improves downstream success rates over existing baselines on CL-Bench and tau2-bench.

0 favorites 0 likes
#skill-generation

@omarsar0: // Automating SKILL.md Generation // Increasingly, mining sessions is one of the best ways to improve your agents. Open…

X AI KOLs Following · 2026-06-19 Cached

This paper from MIT and Harvard explores automating SKILL.md generation by mining GUI interaction trajectories, finding that clusters are readable but do not improve policy performance across domains.

0 favorites 0 likes
#skill-generation

@DanKornas: Writing a good AGENTS.md shouldn’t take weeks of source digging. mimeo is a Python tool that turns an expert’s body of …

X AI KOLs Timeline · 2026-05-23 Cached

mimeo is an open-source Python tool that automatically generates AGENTS.md or SKILL.md files from an expert's body of work, helping coding agents install better defaults.

0 favorites 0 likes
#skill-generation

MIND-Skill: Quality-Guaranteed Skill Generation via Multi-Agent Induction and Deduction

arXiv cs.AI · 2026-05-12 Cached

MIND-Skill is a new framework introduced in this research paper that automates the generation of high-quality, reusable agent skills using multi-agent induction and deduction with quality guarantees via TextGrad optimization.

0 favorites 0 likes
#skill-generation

SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks

Hugging Face Daily Papers · 2026-04-22 Cached

SkillLearnBench introduces the first benchmark for evaluating continual skill learning in LLM agents across 20 real-world tasks, revealing that no method dominates and scaling LLMs does not guarantee better skills.

0 favorites 0 likes
← Back to home

Submit Feedback