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
Figure 1: A representative PushT episode under ACT, beam search, and OSA, starting from the same initial configuration. Columns show approximate environment steps. The blue marker is the agent, the gray T is the movable object, and the colored T marks the target. Blue paths show nominal predictions, gray paths show alternatives, and warm-colored paths show selected chunks. The baseline fails to align the object within 300 steps; the search-based controllers reach the target.
Method
D
C
BW
Avg. sum reward
Avg. max reward
Success (%)
ASR (%)
Runtime (s)
Beam search
2
4
2
90.9
0.77
18
56.4
14
Beam search
4
2
2
90.8
0.78
16
37.5
10
Beam search
4
4
2
90.9
0.77
18
58.23
10
Beam search
4
8
2
94.7
0.77
18
75.6
33
Beam search
4
8
4
103.2
0.81
18
75.0
47
Beam search
4
8
8
92.2
0.80
10
78.5
87
Table 1: PushT beam-search configurations, averaged over 50 episodes. D : tree depth; C : total candidate count per expanded node, including the nominal chunk; BW : beam width. Reward columns report episode-level cumulative and maximum reward, respectively. ASR is the percentage of selections using a perturbed chunk.
Figure 2: Average cumulative reward versus execution horizon H for two beam-search configurations. Shorter horizons invoke search more frequently. Each point summarizes 50 episodes.
Figure 3: One Step Ahead ablation at D=4 , C=8 , and beam widths 2, 4, and 8. Blue: full beam search; green: OSA. Panels show success, average cumulative reward, and runtime. OSA preserves or improves success in these comparisons while reducing computation, although cumulative reward can decrease.
Action-chunking robot policies predict sequences of future actions, but deployment requires choosing how many actions to execute before replanning. The execution horizon trades off feedback frequency against motion continuity. However, success varies non-monotonically with the execution horizon, and the best-performing horizon differs across tasks. These effects make a single fixed horizon unreliable as a default execution strategy across tasks. We propose PACE (Phase-Aware Chunk Execution), a training-free method that selects execution horizons online from predicted action chunks. PACE uses prominent low-speed valleys in the predicted speed profile as candidate replanning boundaries, exploiting the phase-dependent kinematics of manipulation trajectories. By default, PACE calibrates the valley threshold from each task's existing training demonstrations, without task-specific fixed-horizon tuning. On the 50-task RoboTwin2.0 benchmark, PACE improves average success from 57.8% to 64.2% over the strongest fixed-horizon baseline and outperforms the adaptive execution baselines AAC and AutoHorizon. With GR00T N1.7 on LIBERO, PACE achieves the highest overall success rate among the evaluated strategies, supporting its applicability across base policies, benchmarks, and action representations. On real robots, PACE improves the average task score from 60.7 to 77.7 and success rate from 50.7% to 70.4% over full-chunk execution. Code is available at https://niejunnan25.github.io/pace-project/.
Junnan Nie, Jiayi Li, Chenghao Liu +4
Peking University · Peking University. · JD Explore Academy. +1
Vision-Language-Action (VLA) models serve as unified policies for robotic manipulation, yet their expensive inference forces robots to pause between policy calls, resulting in stop-and-go execution that interrupts smooth motion and prolongs task completion. Extending the action chunk reduces policy calls and hence these pauses, but predicting farther into the future makes long-chunk execution unreliable. To understand where this unreliability arises, we analyze action errors within long chunks and find that they concentrate around transitions between manipulation subskills, growing sharply with chunk length. This suggests the importance of transition timing, i.e., when to switch subskills within a chunk. Motivated by this observation, we introduce RACE (Reliable Action-Chunk Extension), a framework that predicts the transition timing from an auxiliary one-step denoising pass and conditions action generation on it. By learning and conditioning on transition timing, RACE reduces errors at subskill transitions and enables reliable execution of longer action chunks. Across simulation benchmarks, RACE outperforms fine-tuning at the same chunk length; with 2x longer chunks, it surpasses recent state-of-the-art and efficient VLAs in success rate, and with 4x longer chunks, it remains competitive. On a real robot, RACE uses 4x longer chunks, which reduces the idle time caused by stop-and-go execution by about 5x, while achieving a higher success rate than fine-tuning with the same chunk length. Code and a real-robot demo are available at https://github.com/Seonghoon-Yu/RACE-VLA
Agentic robotics places a large language model (LLM) agent in the robot control loop, where it composes perception, motion, and vision-language-action (VLA) tools under the guidance of a memory and thereby generalizes to new tasks without retraining. This generality comes at a steep price in efficiency. Every primitive requires a round of LLM reasoning over the full interaction history, so the cost of an episode grows with the number of primitives. We find this reasoning largely redundant: once a sub-goal is chosen, its primitives follow a routine already prescribed by memory. We present ChunkAct, which introduces action chunking to agentic robotics. Online, a single call launches a chunk of chained primitives, which executes autonomously and returns control only upon failure. Offline, ChunkAct compiles the memory into these chunks, so execution is memory-free at test time and the planner is reserved for decisions that require reasoning. LLM computation therefore scales with the number of decisions rather than the number of primitives. On LIBERO-Pro, ChunkAct improves task success by 5.0 points over the state of the art in agentic robotics while requiring 2.9x fewer LLM calls, 4.4x fewer input tokens, and 2.3x fewer output tokens.
Bingxin Xu, Wenrui Bao, Xinxin Liu +3
University of Southern California · University of Central Florida · Stony Brook University