The Purpose I Write This Blog
Amazing agent systems have been created to change our life. I want to keep to collect information about LLM-based agents and share my thoughts here.
Resource
Agentic Learning
survey
- Towards Long-Horizon Agents: A Survey
- The Hitchhiker’s Guide to Agentic AI: From Foundations to Systems
- From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models
Blogs
LLM-based agents
- RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
- RAGEN-2: Reasoning Collapse in Agentic RL
- rStar2-Agent: Agentic Reasoning Technical Report
- (GiGPO) Group-in-Group Policy Optimization for LLM Agent Training
- (ARPO) Agentic Reinforced Policy Optimization
- APPO: Agentic Procedural Policy Optimization
- (AEPO) Agentic Entropy-Balanced Policy Optimization
- Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs
- AgentTuning: Enabling Generalized Agent Abilities for LLMs
VLM-based agents
Multi-agent
- advantage computation
- MARL credit assignment
Self evolution
- harness
- memory
- blogs
- Agent Memory Architectures: Vector vs Graph vs Episodic
- ChatGPT ‘Dreaming V3’ Memory: Self-Updating AI Recall
- Harness Comparison: How Claude Code, Cursor, Devin, and Antigravity Each Handle Memory
- Give Your AI Agent Memory and Guardrails: Mem0 + Docker Sandboxes
- (wiki) Agent Memory Benchmark Guidelines
- 面试官皱眉：“你知道 Claude Code 记忆机制吗？” 我：“何止知道？我还看过源码”，他又愣了…
- non-parameterized memory
- Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
- Mem-α: Learning Memory Construction via Reinforcement Learning
- MemCoRL: Alternating Co-Optimization of Memory Retrieval and Utilization via Collaborative Reinforcement Learning
- MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards
- Dreaming: Better memory for a more helpful ChatGPT
- Codex
- Doubao
- AUTOMEM: Automated Learning of Memory as a Cognitive Skill
- Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
- (M3-Agent) Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
- MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- MemGPT: Towards LLMs as Operating Systems
- parameterized memory
- blogs
- Recursive Self-Improvement (RSI)
- meta-RL
- test-time scaling
- online learning
- benchmark
Data
- Using Grounded Theory for Agent Behavior Analysis at Scale
- Beyond Stochastic Exploration: What Makes Training Data Valuable for Agentic Search
Environment
- Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
- Environment Scaling for Agentic RL
- Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Others
exploration
experience replay
- Efficient RL Training for LLMs with Experience Replay
- Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
- AgentHER: Hindsight Experience Replay for LLM Agent Trajectory
- ARPO1: End-to-End Policy Optimization for GUI Agents with Experience Replay
context management
emergence
general evaluation
On-policy distillation
Blogs
Papers
- AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
- OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning
Coding Agent
survey
blogs
models
- codex
- codex：https://zhuanlan.zhihu.com/p/2029683221646907323
- harness
- claude *
- grok
- harness
- algorithm
- deepseek
- harness
benchmarks
- DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch
- Immersion in the GitHub Universe: Scaling Coding Agents to Mastery
- Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering
GUI Agent
survey
models
- Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
- CUA-GYM:ScalingVerifiableTraining Environments and Tasks for Computer-Use Agents
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- autoglm
- ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents
- MobileRL: Advancing Mobile Use Agents With Adaptive Online Reinforcement Learning
- ANDROIDGEN: Building an Android Language Agent under Data Scarcity
- Autoglm: Autonomous foundation agents for guis
- WebRL:Training llm web agents via self-evolving online curriculum reinforcement learning
- AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents
- DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
- SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents
- Appagent: Multimodal agents as smartphone users
- (SeeAct) GPT-4V(ision) is a Generalist Web Agent, if Grounded
- Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
benchmarks
- web
- ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use
- WebArena: A Realistic Web Environment for Building Autonomous Agents
- Mind2web: Towards a generalist agent for the web
- Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments
- (MiniWob) World of Bits: An Open-Domain Platform for Web-Based Agents
- android
DeepResearch
survey
models
- Search-o1: Agentic search-enhanced large reasoning models
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- R1-searcher: Incentivizing the search capability in llms via reinforcement learning
- (Jina) node-DeepResearch Public
- Kimi-Researcher: End-to-End RL Training for Emerging Agentic Capabilities
- Language Modeling by Language Models