Agents' Last Exam

The original nirholas/claude-code before DMCA and take down. Once everything is cleared, it will return. Working with Anthropic and Github to get everything back.

This is the code repo for the paper AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play (NeurIPS 2025 Spotlight).

Large model-assisted paper review

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Collection of latest papers and materials in the area of RLVR!

Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving

A Survey of Reinforcement Learning for Large Reasoning Models

Official Code Repository for paper "Towards Better Instruction Following Retrieval Models"

[ICLR'26] MedAgentGYM: Training LLM Agents for Code-Based Medical Reasoning at Scale

Official Code Repository for WorkForceAgent-R1

[Patterns] MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning

GeoAI: Artificial Intelligence for Geospatial Data

Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning

[EMNLP 2024] MIMIR: A Streamlined Platform for Personalized Agent Tuning in Domain Expertise https://arxiv.org/abs/2404.04285

Code and data for TrialGPT.

QBRC Somatic Mutation Calling Pipeline

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

[EMNLP'24] MedAdapter: Efficient Test-Time Adaptation of Large Language Models Towards Medical Reasoning

Code for paper Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding