EnactOpt: Diagnosis-Guided Harness Evolution for Embodied Agents
cs.RO
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/OpenMOSS/VLABench
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Qwen3-VL Technical Report
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- PaLM-E: An Embodied Multimodal Language Model
- TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning
- GPT-4o System Card
- HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution
- EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents
- OpenVLA: An Open-Source Vision-Language-Action Model
- Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- ASPIRE: Agentic /Skills Discovery for Robotics
- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
- Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies