RSI-Env: An Open-Ended Environment for Recursive Self-Improvement of Agents
cs.CV
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- Co-Harness: Co-Evolving Harnesses and Model Weights for LLM Agents
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment
- RSIGym: A Flexible Environment for Recursive Self-Improvement
- RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
- SHE: Trajectory-driven Safety Harness Evolution for LLM Agents
- Toolformer: Language Models Can Teach Themselves to Use Tools
- RSI-Forge: From Research Papers to Environments for Recursive Self-Improvement
- ReAct: Synergizing Reasoning and Acting in Language Models
- STaR: Bootstrapping Reasoning With Reasoning
- Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
- Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs