Safety
AtomBridge: Agentic VLA Inference Plugin for Long-Horizon Tasks in Scientific Experiments
arXiv:2602.09430v2 Announce Type: replace-cross Abstract: Robotic laboratories play a critical role in autonomous scientific discovery by enabling scalable, continuous experimental execution. Recent v
arXiv:2602.09430v2 Announce Type: replace-cross Abstract: Robotic laboratories play a critical role in autonomous scientific discovery by enabling scalable, continuous experimental execution. Recent vision-language-action (VLA) models offer a promising foundation for robotic laboratories. However, scientific experiments typically involve long-horizon tasks composed of multiple atomic tasks. Existing VLA models may fail to perform composed tasks formed by reordering and composing these known atomic actions. This limitation can arise from a skill-chaining gap caused by robot-state mismatch: the terminal robot state of one skill can fall outside the valid initial-state distribution of the next. To address this challenge, we propose AtomBridge, an Agentic VLA Inference Plugin for Long-Horizon Tasks in Scientific Experiments. AtomBridge attaches at inference time to a VLA policy already fine-tuned on atomic tasks, while keeping its weights fixed. At each task boundary, it uses LLM-based transition reasoning and robotic-action code generation to insert transitional actions between consecutive tasks. This plug-and-play design mitigates the skill-chaining gap caused by robot-state mismatch without additional VLA fine-tuning or demonstrations of composed long-horizon sequences. Across scientific manipulation sequences in simulation and a real-world experimental environment, AtomBridge improves execution continuity and per-step atomic-task success. On 8-step composed tasks, AtomBridge improves full-sequence success by 10%~25%.
Related
- Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks
- Beyond Policy Optimization: A Data Curation Flywheel for Sparse-Reward Long-Horizon Planning
- HiPER: Hierarchical Reinforcement Learning with Explicit Credit Assignment for Large Language Model Agents
- The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation
Source: arXiv cs.AI | 2026-08-17