Define your problem and evaluation criteria — EurekAgent coordinates off-the-shelf CLI agents to propose diverse approaches, implement them, run experiments, and iterate. Human intervention is opti…

LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards

Deep-dive notes and source code analysis of Claude Code and AI agent harnesses. Exploring memory mechanics and internal architectures.

💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minec…

Composable HLS library for rapid development of LLM accelerators. FlexLLM enables spatial-temporal hybrid architectures, with parameterized modulet templates customized for the prefill and decode s…

This repository contains the code and data for the paper "Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards".

Official Repository for "Glyph: Scaling Context Windows via Visual-Text Compression"

Tongyi Deep Research, the Leading Open-source Deep Research Agent

DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL

TradingAgents: Multi-Agents LLM Financial Trading Framework

slime is an LLM post-training framework for RL Scaling.

Official Implementation for the paper "d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning"

🙌 OpenHands: AI-Driven Development

[NIPS 2025 DB Spotlight] AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios

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"

Model Context Protocol Servers

Pioneering Automated GUI Interaction with Native Agents

A live stream development of RL tunning for LLM agents

Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.

Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods on large reasoning models. It contains papers, codes, datasets, evaluations, and analyses.

An invisible desktop application to help you pass your technical interviews.

[ICLR 25 Oral] RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

o1 Chain of Thought Examples

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA

An awesome repository & A comprehensive survey on interpretability of LLM attention heads.