AMBER: Training Long-Horizon Web Agents through Append-Only Memory
cs.AI, cs.LG
Submitted: 2026-10-05
Updated: 2026-10-05
Code: https://github.com/agentic-foundation-modeling-research/amber
Sources
- The BrowserGym Ecosystem for Web Agent Research
- On the Multi-turn Instruction Following for Conversational Web Agents
- Go-Browse: Training Web Agents with Structured Exploration
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents
- NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wild
- MemGPT: Towards LLMs as Operating Systems
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Reflexion: Language Agents with Verbal Reinforcement Learning
- How to Train Your LLM Web Agent: A Statistical Diagnosis
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
- Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
- ReAct: Synergizing Reasoning and Acting in Language Models
- AgentFold: Long-Horizon Web Agents with Proactive Context Management
- MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
- MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning
- Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
- ExpeL: LLM Agents Are Experiential Learners
- WebArena: A Realistic Web Environment for Building Autonomous Agents
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems