Stars
[ICML 2026] Milestone-Guided Policy Learning for Long-Horizon Language Agents
The papers and code related to deep generative models for material discovery.
An active paper-reading skill that reconstructs author reasoning, explains methods mechanistically, stress-tests assumptions, and generates follow-up research ideas.
ICML 2026 autonomous AI agent for end-to-end spatial proteomics analysis, with SP-Bench for agentic multiplexed-imaging workflows.
Framework for evaluating and improving agents
【ICML2026 Spotlight】 T2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning
Scholar All-In-One: A research infrastructure for AI agents
Collection of Summer, Fall, Spring 2027 tech internships!
A collection of full time roles in SWE, Quant, and PM for new grads.
[CVPR 25] A framework named B^2-DiffuRL for RL-based diffusion model fine-tuning.
The offical repo for "Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing"
This codebase is to reproduce the results of the paper "Grounded Test-Time Adaptation for LLM Agents".
Offical implementation of "Life-Harness"
Skill package for ML/CV/NLP paper writing, curated and adapted from Prof. Peng Sida's open notes for Codex, Claude Code, and Gemini.
A collection of reinforcement learning environments for simple web interaction tasks
TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.
Evolutionary Generation of Multi-Agent Systems; Yuntong Hu, Yuting Zhang, Matthew Trager, Yi Zhang, Shuo Yang, Wei Xia, Stefano Soatto, ICML 2026
CATArena is an engineering-level tournament evaluation platform for Large Language Model-driven code agents (LLM-driven code agents), based on an iterative competitive peer learning framework.
[ICML 2026] Principle-Evolvable Scientific Discovery via Uncertainty Minimization
(ICML 2026) Self‑Evolving LLM Agents through an Experience‑Driven Lifecycle