aiming-lab

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

[ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal

🦞 Just talk to your agent — it learns and EVOLVES 🧬.

[ICML'26 & COLM'26] Agent0 Series: Self-Evolving Agents from Zero Data

[NeurIPS'26] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

AutoHarness: Automated Harness Engineering for AI Agents

MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding

RSI-Exam: Measuring Recursive Self-Improvement on Long-Horizon, Executable Research Tasks · Discord https://discord.gg/FBzhepyE

[ICRA'26] GRAPE: Guided-Reinforced Vision-Language-Action Preference Optimization

[ICML'25] MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization

WebHarbor: Docking Real Websites for Evolving GUI Agent Environments

[NeurIPS'25] ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding