Tag
Introduces HExA, a training-free framework enabling LLMs to learn through active experimentation and skill reuse, achieving up to 77% success on the new Interphyre physics benchmark, a large improvement over existing agents.
Matt Pocock demonstrates that he can solve a Rubik's cube after learning from an AI's /teach skill, proving AI can effectively teach hands-on skills.
Memento-Skills is a self-evolving agent framework where agents learn from failures and rewrite their own skills, improving over time through a Read-Execute-Reflect-Write loop. It was tested on HLE and GAIA benchmarks and supports open-source LLMs like Kimi, MiniMax, and GLM.
This paper proposes SGDR (State-Grounded Dynamic Retrieval), an online skill learning method for web agents that enables stepwise, state-aware skill reuse rather than static task-level retrieval. Experiments on WebArena show SGDR achieves 37.5% success rate with GPT-4.1, a ~10.6% relative gain over strong baselines.
该论文提出 FluxMem，一种将智能体记忆视为不断演化的图结构，通过动态修复连接和提炼技能来提升记忆效果的系统。实验显示其在多个任务上优于现有方法，例如在 LoCoMo 上达到 95.06% 准确率，并在 GAIA 上相比 Kimi K2 提升 12.73 分。
SkillHarness is a framework that enables computer-use agents to safely learn and execute skills in dynamic environments by incorporating safety constraints and adaptive skill selection mechanisms, reducing unsafe rates by 57.1%.
MMG2Skill converts web-based procedural guides into executable skills for agents through closed-loop learning, improving performance across GUI control, gameplay, and card play tasks with macro-average gains of +12.8 to +25.3 percentage points.
This paper introduces 'constant-context skill learning,' a framework that moves procedural knowledge from prompts into model weights to reduce token usage and improve privacy for LLM agents. The method achieves strong performance on benchmarks like ALFWorld and WebShop while significantly reducing inference costs.
OpenAI researchers propose a framework using stochastic neural networks for hierarchical reinforcement learning that pre-trains useful skills guided by a proxy reward, then leverages these skills for faster learning in downstream tasks with sparse rewards or long horizons.