# A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning

arXiv: https://arxiv.org/abs/2512.14442 · HTML: https://mlsanity.com/paper/2512.14442/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 32 of its 59 references that are in the map.
- First posted on arXiv 16 Dec 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 32)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement](https://mlsanity.com/paper/2503.06520/) (2025)
- [Imagine while Reasoning in Space: Multimodal Visualization-of-Thought](https://mlsanity.com/paper/2501.07542/) (2025)
- [Human-to-Robot Imitation in the Wild](https://mlsanity.com/paper/2207.09450/) (2022)
- [Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond](https://mlsanity.com/paper/2405.03520/) (2024)
- [Thinking with Generated Images](https://mlsanity.com/paper/2505.22525/) (2025)
- [Detect Anything via Next Point Prediction](https://mlsanity.com/paper/2510.12798/) (2025)
- [VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning](https://mlsanity.com/paper/2505.12081/) (2025)
- [Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark](https://mlsanity.com/paper/2510.26802/) (2025)
- [Ditto in the House: Building Articulation Models of Indoor Scenes through Interactive Perception](https://mlsanity.com/paper/2302.01295/) (2023)
- [3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds](https://mlsanity.com/paper/2502.20041/) (2025)
- [GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding](https://mlsanity.com/paper/2411.19626/) (2024)
- [Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model](https://mlsanity.com/paper/2508.06206/) (2025)
- [Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding](https://mlsanity.com/paper/2408.13024/) (2024)
- [TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models](https://mlsanity.com/paper/2511.13704/) (2025)
- [ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback](https://mlsanity.com/paper/2505.17908/) (2025)
- [GLOVER++: Unleashing the Potential of Affordance Learning from Human Behaviors for Robotic Manipulation](https://mlsanity.com/paper/2505.11865/) (2025)
- [DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation](https://mlsanity.com/paper/2511.23127/) (2025)

## Built on by (most cited first, 5 of 5)

- [Affordance Agent Harness: Verification-Gated Skill Orchestration](https://mlsanity.com/paper/2605.00663/) (2026)
- [Panoramic Affordance Prediction](https://mlsanity.com/paper/2603.15558/) (2026)
- [A3R: Agentic Affordance Reasoning via Cross-Dimensional Evidence in 3D Gaussian Scenes](https://mlsanity.com/paper/2604.01882/) (2026)
- [SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding](https://mlsanity.com/paper/2605.14923/) (2026)
- [Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent Arena](https://mlsanity.com/paper/2610.00854/) (2026)

## Abstract (arXiv)

Affordance prediction, which identifies interaction regions on objects based on language instructions, is critical for embodied AI. Prevailing end-to-end models couple high-level reasoning and low-level grounding into a single monolithic pipeline and rely on training over annotated datasets, which leads to poor generalization on novel objects and unseen environments. In this paper, we move beyond this paradigm by proposing A4-Agent, a training-free agentic framework that decouples affordance prediction into a three-stage pipeline. Our framework coordinates specialized foundation models at test time: (1) a Dreamer that employs generative models to visualize textithow an interaction would look; (2) a Thinker that utilizes large vision-language models to decide textitwhat object part to interact with; and (3) a Spotter that orchestrates vision foundation models to precisely locate textitwhere the interaction area is. By leveraging the complementary strengths of pre-trained models without any task-specific fine-tuning, our zero-shot framework significantly outperforms state-of-the-art supervised methods across multiple benchmarks and demonstrates robust generalization to real-world settings.