# Harnessing Multimodal Large Language Models for Training-Free Human-Object Interaction Detection

arXiv: https://arxiv.org/abs/2610.06394 · HTML: https://mlsanity.com/paper/2610.06394/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 11 of its 75 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 11 of 11)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Visual Semantic Role Labeling](https://mlsanity.com/paper/1505.04474/) (2015)
- [What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generation](https://mlsanity.com/paper/2602.11499/) (2026)
- [HOID-R1: Reinforcement Learning for Open-World Human-Object Interaction Detection Reasoning with Multimodal Large Language Model](https://mlsanity.com/paper/2508.11350/) (2025)
- [Propose and Attend: Training-free MLLM Grounding Confidence via Multi-Token Localized Attention](https://mlsanity.com/paper/2607.05978/) (2026)
- [An analysis of HOI: using a training-free method with multimodal visual foundation models when only the test set is available, without the training set](https://mlsanity.com/paper/2408.05772/) (2024)
- [HOI-R1: Exploring the Potential of Multimodal Large Language Models for Human-Object Interaction Detection](https://mlsanity.com/paper/2510.05609/) (2025)
- [ScriptHOI: Learning Scripted State Transitions for Open-Vocabulary Human-Object Interaction Detection](https://mlsanity.com/paper/2605.05057/) (2026)
- [Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual Reasoning](https://mlsanity.com/paper/2605.29894/) (2026)
- [HOIBlender: Blending Lightweight Detection with Vision-Language Priors for Efficient Human-Object Interaction Detection](https://mlsanity.com/paper/2609.23431/) (2026)

## Abstract (arXiv)

Human-object interaction (HOI) detection aims to localize human-object pairs and recognize their interactions. Traditional supervised methods perform strongly but rely on task-specific training. Recent multimodal large language models (MLLMs) offer a promising route to training-free HOI detection through their broad visual-semantic knowledge and versatile perceptual and reasoning capabilities. However, existing approaches largely invoke these capabilities through loosely coordinated inference stages. This fragmented execution restricts the role of interaction hypotheses in guiding visual exploration, leaving key participants overlooked and local ambiguities unresolved. Furthermore, propagating early semantic assumptions through subsequent visual grounding and relation prediction induces self-reinforcing semantic circularity. To resolve these challenges, we propose HarnessHOI, a training-free framework that transforms passive MLLM inference into an active interaction-centric harness. Specifically, we introduce an interaction-guided perception mechanism that projects emerging interaction hypotheses back into the visual space to discover missing participants and refine ambiguous evidence through targeted observation. Furthermore, a relation-agnostic geometric adjudication module reconciles multi-source evidence to establish a unified spatial basis for grounded interaction reasoning across multiple actions and semantic roles. Extensive experiments on HICO-DET and V-COCO demonstrate that HarnessHOI achieves state-of-the-art performance among training-free methods, confirming the effectiveness of the proposed harness for complex interaction understanding. Code will be released upon publication.