Code for our paper: Retrievable Gradients

An open-source AI agent that lives in your terminal.

The open source coding agent improved with IR techniques.

Awesome List for Agentic RL

s1: Simple test-time scaling

Code for Multi-Field Tool Retrieval

Orthogonal Subspace Decomposition

SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.

Repo for paper "Agentic-R: Learning to Retrieve for Agentic Search" (ACL 2026 Findings)

A smart skill search engine for agents with multi-field retrieval and quality signals.

Source code of our SIGIR 2026 paper: "Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization"

LegalOne: A Family of Foundation Models for Reliable Legal Reasoning

Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — with sandbox isolation, multi-model support, and Feishu/Slack integration.

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

Public repository for Agent Skills

[AAAI'26, Oral] Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG

Code for MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems

用于从谷歌学术上爬取SIGIR上论文的引用数

Source code of DRAGIN, ACL 2024 main conference Long Paper (Oral)

Unified Automated Evaluation for Hallucination Detection and Fact Verification

Implementation of "ACL'24: When Do LLMs Need Retrieval Augmentation? Mitigating LLMs’ Overconfidence Helps Retrieval Augmentation"

Code for State Delta Encoding

BenCourt: A Benchmark and Framework for Court Simulation using LLM-based Agents

Code for RACE.