Pinned Loading

1. microsoft/SkillOpt microsoft/SkillOpt Public

   SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

   Python 5.8k 574

2. microsoft/SkillLens microsoft/SkillLens Public

   SkillLens: a framework for studying model-generated agent skills across the full raw experience generation → skill extraction → skill consumption lifecycle.

   Python 92 9

3. query-refinement query-refinement Public

   Implementation of paper "Enhancing the Capability and Robustness of Large Language Models through Reinforcement Learning-Driven Query Refinement" (https://arxiv.org/abs/2407.01461).

   Python 2

4. Moore-Tian/SteeM-Memory-Control Moore-Tian/SteeM-Memory-Control Public

   Code, prompts, evaluation, and curated examples for "Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction".

   Python 1