# BoT-Feedback: Grounding Multimodal Reasoning in Biomechanical Evidence for Explainable Human Action Feedback

arXiv: https://arxiv.org/abs/2610.06972 · HTML: https://mlsanity.com/paper/2610.06972/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 21 of its 48 references that are in the map.
- First posted on arXiv 3 Oct 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 21 of 21)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [Soft-DTW: a Differentiable Loss Function for Time-Series](https://mlsanity.com/paper/1703.01541/) (2017)
- [Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition](https://mlsanity.com/paper/2501.03230/) (2024)
- [Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs](https://mlsanity.com/paper/1703.08014/) (2017)
- [Chain of Thoughtlessness? An Analysis of CoT in Planning](https://mlsanity.com/paper/2405.04776/) (2024)
- [Learning To Score Olympic Events](https://mlsanity.com/paper/1611.05125/) (2016)
- [Action Quality Assessment Across Multiple Actions](https://mlsanity.com/paper/1812.06367/) (2018)
- [Learning to score the figure skating sports videos](https://mlsanity.com/paper/1802.02774/) (2018)
- [The Pros and Cons: Rank-aware Temporal Attention for Skill Determination in Long Videos](https://mlsanity.com/paper/1812.05538/) (2018)
- [SAM 3D Body: Robust Full-Body Human Mesh Recovery](https://mlsanity.com/paper/2602.15989/) (2026)
- [FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment](https://mlsanity.com/paper/2405.06887/) (2024)
- [Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption](https://mlsanity.com/paper/2404.11291/) (2024)
- [PhysVLM: Enabling Visual Language Models to Understand Robotic Physical Reachability](https://mlsanity.com/paper/2503.08481/) (2025)
- [CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignment](https://mlsanity.com/paper/2404.13999/) (2024)
- [Explainable Action Form Assessment by Exploiting Multimodal Chain-of-Thoughts Reasoning](https://mlsanity.com/paper/2512.15153/) (2025)
- [FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessment](https://mlsanity.com/paper/2503.23911/) (2025)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in visual understanding and multimodal reasoning, yet they remain fundamentally limited in Human Action Feedback Generation. Existing methods infer coaching feedback directly from visual observations, producing generic advice, limited interpretability, and physically implausible hallucinations. In contrast, expert human coaches diagnose performance through explicit biomechanical reasoning over joint kinematics, posture, and body dynamics. We introduce BoT-Feedback, a framework that grounds MLLM reasoning in structured biomechanical evidence. Our key contribution is Biomechanics of Thought (BoT), a four-stage reasoning framework that progressively identifies the action, localises the critical body regions, analyses quantitative biomechanical differences between expert and student performances, and synthesises interpretable coaching feedback. To support this reasoning process, we develop a plug-and-play Biomechanical Data Parser (BDP) that converts videos into structured biomechanical descriptors and an alignment strategy that temporally matches expert and student motions. We further introduce BiomAF, a benchmark containing paired teacher-student videos, 3D skeletons, biomechanical attributes, and expert-coaching annotations. Experiments across twelve open- and closed-source MLLMs demonstrate that grounding reasoning in biomechanical evidence consistently improves feedback quality, interpretability, and robustness while substantially reducing biomechanical hallucinations. BoT-Feedback improves the average expert evaluation score from 2.07 to 2.95 (+40%), enabling compact open-source MLLMs to approach the performance of substantially larger proprietary systems for explainable action feedback generation.