Research

Paper

AI LLM February 24, 2026

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

Authors

Yining Hong, Huang Huang, Manling Li, Li Fei-Fei, Jiajun Wu, Yejin Choi

Abstract

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 ablative studies validating the complementary roles of reflection-in-action and reflection-on-action. Qualitative analyses, including real-robot trials, highlight behavioral correction through reflection.

Metadata

arXiv ID: 2602.21198
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-02-24
Fetched: 2026-02-25 06:05

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.21198v1</id>\n    <title>Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs</title>\n    <updated>2026-02-24T18:55:18Z</updated>\n    <link href='https://arxiv.org/abs/2602.21198v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.21198v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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 ablative studies validating the complementary roles of reflection-in-action and reflection-on-action. Qualitative analyses, including real-robot trials, highlight behavioral correction through reflection.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.RO'/>\n    <published>2026-02-24T18:55:18Z</published>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Yining Hong</name>\n    </author>\n    <author>\n      <name>Huang Huang</name>\n    </author>\n    <author>\n      <name>Manling Li</name>\n    </author>\n    <author>\n      <name>Li Fei-Fei</name>\n    </author>\n    <author>\n      <name>Jiajun Wu</name>\n    </author>\n    <author>\n      <name>Yejin Choi</name>\n    </author>\n  </entry>"
}