REINS: A Self-Evolving Agent Harness for Real-Time Trajectory Planning
cs.RO, cs.AI
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/ZhihongCui/REINS
Terminology
Sources
- NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles
- Driving with Regulation: Trustworthy and Interpretable Decision-Making for Autonomous Driving with Retrieval-Augmented Reasoning
- Meta-Harness: End-to-End Optimization of Model Harnesses
- WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving
- LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
- Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models
- Integrating Legal and Logical Specifications in Perception, Prediction, and Planning for Automated Driving: A Survey of Methods
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
- LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving
- On a Formal Model of Safe and Scalable Self-driving Cars
- Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- ADRD: LLM-Driven Autonomous Driving Based on Rule-based Decision Systems
- LeAD: The LLM Enhanced Planning System Converged with End-to-end Autonomous Driving
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation