The official implementation of the paper "Mem-α: Learning Memory Construction via Reinforcement Learning"

Scaling Long-Horizon LLM Agent via Context-Folding

AgentFlow: In-the-Flow Agentic System Optimization

SWE-Exp: Experience-Driven Software Issue Resolution

Building Open LLM Web Agents with Self-Evolving Online Curriculum RL

A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.

AWM: Agent Workflow Memory

[EMNLP 2025] WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning

Setup scripts for the WebArena benchmark

[ICLR 2026] Official Implementation of ProxyThinker: Test-Time Guidance through Small Visual Reasoners.

[EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)

Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning (NeurIPS2025-SEA)

[NeurIPS'25] The official code implementation for paper "R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing"

[ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples

Reasoning Activation in LLMs via Small Model Transfer (NeurIPS 2025)

Some special ebooks，一些个人喜欢同时也比较特别的电子书

Structured Chemistry Reasoning with Large Language Models

A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery (EMNLP'24)

The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions (EMNLP 2023))

Daily updated LLM papers. 每日更新 LLM 相关的论文，欢迎订阅 👏 喜欢的话动动你的小手 🌟 一个

Codes for our paper "Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation" (EMNLP 2023 Findings)

A curated list for Efficient Large Language Models

Code for "Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective"

Code and dataset for the emnlp paper titled Instruct and Extract: Instruction Tuning for On-Demand Information Extraction

[ICLR 2024] Lemur: Open Foundation Models for Language Agents

Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**

A curated list of papers and resources based on "Large Language Models on Graphs: A Comprehensive Survey" (TKDE)

contrastive decoding