cs.AINov 7, 2026

Look Ahead: Search-Driven Reasoning in Embodied AI

Authors: Ahmed Zeer, Osama Shbib, Muzaffer Kaan Yuce, Himmet Toprak Kesgin, Mehmet Fatih Amasyali

Organizations: Department of Computer Engineering, Yildiz Technical University, Istanbul, Türkiye.

Abstract

Search allows a robotic policy to evaluate candidate futures before committing to an action. Motivated by test-time planning for vision-language action (VLA) models, we study selective search over action chunks in PushT using a frozen Action Chunking with Transformers (ACT) policy. Beam search generates perturbed alternatives around the policy prediction and scores them through rollouts from cloned simulator states. Across 50 evaluation episodes, beam search raises task success from 0% to 18% and increases average cumulative reward from 39.44 to 103.2. We introduce One Step Ahead (OSA), a gate that simulates the nominal policy chunk and invokes full search only when its predicted coverage drop exceeds a threshold. In the reported ablations, OSA preserves or improves success while reducing runtime by approximately 3x relative to full beam search. Ablations over tree depth, branching factor, beam width, and replanning frequency show that larger search budgets do not consistently improve performance. The results support selective test-time search for action-chunking policies; evaluation on language-conditioned VLAs and physical robots remains future work.

Figures & tables

Explore similar work

CardsList
  1. PACE: Phase-Aware Chunk Execution for Robot Policies with Action Chunking

    May 30, 2026Junnan Nie, Jiayi Li, Chenghao Liu +4Robotic ManipulationAction Chunking

  2. When to Switch: Reliable Action-Chunk Extension for Vision-Language-Action Models

    Oct 5, 2026Seonghoon Yu, Dongwon Kim, HyungRok Jung +4Efficient VLA InferenceRobotic Manipulation

  3. ChunkAct: Action Chunking for Agentic Robotics

    Oct 13, 2026Bingxin Xu, Wenrui Bao, Xinxin Liu +3Agentic AI for RoboticsRobotics