# Mitigating Cross-Modal Distraction and Ensuring Geometric Feasibility via Affordance-Guided and Self-Consistent MLLMs for Task Planning in Instruction-Following Manipulation

arXiv: https://arxiv.org/abs/2503.13055 · HTML: https://mlsanity.com/paper/2503.13055/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 17 Mar 2025.

## Placed in

- 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, 24 of 24)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021)
- [HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models](https://mlsanity.com/paper/2310.14566/) (2023)
- [Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning](https://mlsanity.com/paper/2306.14565/) (2023)
- [Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents](https://mlsanity.com/paper/2302.01560/) (2023)
- [Integrated Task and Motion Planning](https://mlsanity.com/paper/2010.01083/) (2020)
- [Text2Motion: From Natural Language Instructions to Feasible Plans](https://mlsanity.com/paper/2303.12153/) (2023)
- [Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning](https://mlsanity.com/paper/2311.17842/) (2023)
- [Vision-Language Models as Success Detectors](https://mlsanity.com/paper/2303.07280/) (2023)
- [DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignment](https://mlsanity.com/paper/2307.00329/) (2023)
- [Soft Self-Consistency Improves Language Model Agents](https://mlsanity.com/paper/2402.13212/) (2024)
- [DKPROMPT: Domain Knowledge Prompting Vision-Language Models for Open-World Planning](https://mlsanity.com/paper/2406.17659/) (2024)
- [Socratic Planner: Self-QA-Based Zero-Shot Planning for Embodied Instruction Following](https://mlsanity.com/paper/2404.15190/) (2024)
- [FlowPlan: Zero-Shot Task Planning with LLM Flow Engineering for Robotic Instruction Following](https://mlsanity.com/paper/2503.02698/) (2025)
- [REPeat: A Real2Sim2Real Approach for Pre-acquisition of Soft Food Items in Robot-assisted Feeding](https://mlsanity.com/paper/2410.10017/) (2024)

## Abstract (arXiv)

We investigate the use of Multimodal Large Language Models (MLLMs) with in-context learning for closed-loop task planning in instruction-following manipulation. We identify four essential requirements for successful task planning: quantity estimation, reachability analysis, relative positioning, and collision avoidance. However, existing benchmarks fail to support holistic evaluation across all these aspects. To address this gap, we introduce QuARC (Quantity, Analysis, Relative positioning, Collision), a new benchmark based on a food preparation scenario that integrates all four challenges. Using QuARC, we reveal two major limitations of current MLLMs: cross-modal distraction and geometric infeasibility. To tackle these, we adapt Chain-of-Thought with Self-Consistency to mitigate reasoning loss from cross-modal distractions and incorporate an affordance predictor to guide planning based on geometric feasibility. Our comprehensive evaluation analyzes performance across multiple baselines and explains sources of improvement. Our method achieves a 76.7% success rate on the benchmark, significantly outperforming the ViLa baseline (36.7%), without requiring additional finetuning. Code and dataset are available at https://hcis-lab.github.io/Affordance-Guided-Self-Consistent-MLLM.