Stars
LLM agent for electricity-computing co-scheduling, with the ECBench benchmark
An agentic framework for omni-modal question-answer tasks.
ICML 2026 "On the Salience of Low-Probability Tokens for AI-Generated Text Detection: A Multiscale Uncertainty Perspective"
Official code and metadata release for ERGeoBench, a benchmark for embodied reasoning and geo-localization in multimodal large language models.
Official implementation of AutoBM: physically consistent and simulation-executable programmatic generation for scientific modeling.
The first standardized multi-task multimodal benchmark for lung cancer clinical decision support.
ONOTE: A comprehensive benchmark for evaluating omnimodal LLMs on Symbolic Music Processing across Staff, Jianpu, and Guitar Tablature with deterministic, zero-hallucination metrics
🔬🦞 A self-evolving AI research colleague for scientists. 285 skills, zero hallucination, persistent memory.
NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models
FlowSteer: agents designing agentic workflows via reinforced progressive canvas editing.
[ICLR 2026] Official resources of "Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding"
LexGenius: An Expert-Level Benchmark for Large Language Models in Chinese Legal General Intelligence
[NeurIPS 2025] Official Repo of Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
The official implementation of "HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs" (ICLR 2026)
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning
[AAAI 2026 Oral] From Stimuli to Minds: Enhancing Psychological Reasoning in LLMs via Bilateral Reinforcement Learning
MiroRL is an MCP-first reinforcement learning framework for deep research agent.
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
[ACL-2026] MMSearch-R1 is an end-to-end RL framework that enables LMMs to perform on-demand, multi-turn search with real-world multimodal search tools.
Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning