LegoEnv: Self-Evolving Agentic Environments via Modular Recombination
cs.CL, cs.AI
Submitted: 2026-11-01
Updated: 2026-11-01
Code: https://github.com/JazyJiang/LegoEnv
Terminology
Sources
- AutoForge: Automated Environment Synthesis for Agentic Reinforcement Learning
- Agent-RLVR: Training Software Engineering Agents via Guidance and Environment Rewards
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
- Agentic Reinforced Policy Optimization
- Towards General Agentic Intelligence via Environment Scaling
- ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
- MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering
- GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators
- VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- SPADE: Self-Play in Adaptive Synthetic Executable Environments
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Training Software Engineering Agents and Verifiers with SWE-Gym
- Meta-Task: Turning Terminal Task Synthesis into a Terminal Task for Scalable Agent Training
- LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents
- APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data