Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hong, Yining, Huang, Huang, Li, Manling, Fei-Fei, Li, Guibas, Leonidas, Wu, Jiajun, Choi, Yejin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918520612192256
author Hong, Yining
Huang, Huang
Li, Manling
Fei-Fei, Li
Guibas, Leonidas
Wu, Jiajun
Choi, Yejin
author_facet Hong, Yining
Huang, Huang
Li, Manling
Fei-Fei, Li
Guibas, Leonidas
Wu, Jiajun
Choi, Yejin
contents Embodied LLMs endow robots with high-level task reasoning, but they cannot reflect on what went wrong or why, turning deployment into a sequence of independent trials where mistakes repeat rather than accumulate into experience. Drawing upon human reflective practitioners, we introduce Reflective Test-Time Planning, which integrates two modes of reflection: \textit{reflection-in-action}, where the agent uses test-time scaling to generate and score multiple candidate actions using internal reflections before execution; and \textit{reflection-on-action}, which uses test-time training to update both its internal reflection model and its action policy based on external reflections after execution. We also include retrospective reflection, allowing the agent to re-evaluate earlier decisions and perform model updates with hindsight for proper long-horizon credit assignment. Experiments on our newly-designed Long-Horizon Household benchmark and MuJoCo Cupboard Fitting benchmark show significant gains over baseline models, with zero-shot generalization to photorealistic HM3D environments and real-robot experiments on a Franka Panda arm. Ablations confirm that reflection-in-action and reflection-on-action are mutually dependent, and that retrospective reflection achieves better credit assignment than step-wise external feedback at lower computational overhead. Qualitative analyses further highlight behavioral correction through reflection.
format Preprint
id arxiv_https___arxiv_org_abs_2602_21198
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
Hong, Yining
Huang, Huang
Li, Manling
Fei-Fei, Li
Guibas, Leonidas
Wu, Jiajun
Choi, Yejin
Machine Learning
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
Robotics
Embodied LLMs endow robots with high-level task reasoning, but they cannot reflect on what went wrong or why, turning deployment into a sequence of independent trials where mistakes repeat rather than accumulate into experience. Drawing upon human reflective practitioners, we introduce Reflective Test-Time Planning, which integrates two modes of reflection: \textit{reflection-in-action}, where the agent uses test-time scaling to generate and score multiple candidate actions using internal reflections before execution; and \textit{reflection-on-action}, which uses test-time training to update both its internal reflection model and its action policy based on external reflections after execution. We also include retrospective reflection, allowing the agent to re-evaluate earlier decisions and perform model updates with hindsight for proper long-horizon credit assignment. Experiments on our newly-designed Long-Horizon Household benchmark and MuJoCo Cupboard Fitting benchmark show significant gains over baseline models, with zero-shot generalization to photorealistic HM3D environments and real-robot experiments on a Franka Panda arm. Ablations confirm that reflection-in-action and reflection-on-action are mutually dependent, and that retrospective reflection achieves better credit assignment than step-wise external feedback at lower computational overhead. Qualitative analyses further highlight behavioral correction through reflection.
title Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
topic Machine Learning
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2602.21198