A3R: Agentic Affordance Reasoning via Cross-Dimensional Evidence in 3D Gaussian Scenes

• URL: http://arxiv.org/abs/2604.01882v1
• Date: Thu, 02 Apr 2026 10:40:51 GMT
• Title: A3R: Agentic Affordance Reasoning via Cross-Dimensional Evidence in 3D Gaussian Scenes
• Abstract summary: Affordance reasoning aims to identify the region that supports the action specified by a given text instruction in complex environments.<n>We propose A3R, an agentic affordance reasoning framework that enables an MLLM-based policy to iteratively select evidence acquisition actions.<n>Experiments on scene-level benchmarks show that A3R consistently surpasses static one-shot baselines.
• Score: 115.37391672369914
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Affordance reasoning in 3D Gaussian scenes aims to identify the region that supports the action specified by a given text instruction in complex environments. Existing methods typically cast this problem as one-shot prediction from static scene observations, assuming sufficient evidence is already available for reasoning. However, in complex 3D scenes, many failure cases arise not from weak prediction capacity, but from incomplete task-relevant evidence under fixed observations. To address this limitation, we reformulate fine-grained affordance reasoning as a sequential evidence acquisition process, where ambiguity is progressively reduced through complementary 3D geometric and 2D semantic evidence. Building on this formulation, we propose A3R, an agentic affordance reasoning framework that enables an MLLM-based policy to iteratively select evidence acquisition actions and update the affordance belief through cross-dimensional evidence acquisition. To optimize such sequential decision making, we further introduce a GRPO-based policy learning strategy that improves evidence acquisition efficiency and reasoning accuracy. Extensive experiments on scene-level benchmarks show that A3R consistently surpasses static one-shot baselines, demonstrating the advantage of agentic cross-dimensional evidence acquisition for fine-grained affordance reasoning in complex 3D Gaussian scenes.

Related papers

• Disentangling 3D Modeling from Spatial Reasoning [56.3819096070689]
  We explore an alternative paradigm for spatial reasoning by explicitly disentangling 3D perception from reasoning.<n>Our key observation is that modern perception models excel at estimating continuous 3D geometry, whereas large language models (LLMs) are particularly effective at compositional and symbolic reasoning.<n>Motivated by these complementary strengths, we propose the Disentangled Spatial Reasoner (DiSR)<n>DiSR reconstructs the physical world into structured 3D evidence using off-the-shelf expert perception models and fine-tunes an LLM with LoRA to perform reasoning solely over this explicit geometric evidence.
  arXiv  Detail & Related papers  (2026-08-05T14:32:48Z)
• R-APS: Compositional Reasoning and In-Context Meta-Learning for Constrained Design via Reflective Adversarial Pareto Search [18.8323743697237]
  Large language models (LLMs) are fluent on open-ended tasks, yet in agentic settings, fluency does not ensure reliable delivery.<n>We trace this gap to three coupled structural failures: errors propagate without localization, worst-case perturbations go unevaluated, and accumulated knowledge is never invalidated.<n>We argue these share a root cause: abductive, counterfactual, meta-inductive, corrective, and inductive reasoning pull a shared context in incompatible directions.
  arXiv  Detail & Related papers  (2026-06-03T12:45:39Z)
• GaussExplorer: 3D Gaussian Splatting for Embodied Exploration and Reasoning [55.826192239140596]
  GaussExplorer is a framework for embodied exploration and reasoning built on 3D Gaussian Splatting (3DGS)<n>We introduce Vision-Language Models (VLMs) on top of 3DGS to enable question-driven exploration and reasoning within 3D scenes.
  arXiv  Detail & Related papers  (2026-01-19T15:17:58Z)
• Mono3DV: Monocular 3D Object Detection with 3D-Aware Bipartite Matching and Variational Query DeNoising [0.6423989407081764]
  Mono3DV is a novel Transformer-based framework for 3D object detection.<n>We develop a 3D-Aware Bipartite Matching strategy that directly incorporates 3D geometric information into the matching cost.<n>Second, it is important to stabilize the Bipartite Matching to resolve the instability occurring when integrating 3D attributes.
  arXiv  Detail & Related papers  (2026-01-03T02:06:28Z)
• Photorealistic Phantom Roads in Real Scenes: Disentangling 3D Hallucinations from Physical Geometry [17.571800971505787]
  This paper introduces the first end-to-end framework to probe, quantify, and tame this unquantified safety risk.<n>To probe, we present 3D-Mirage, the first benchmark of real-world illusions with precise planar-region annotations and context-restricted crops.<n>To quantify, we propose a Laplacian-based evaluation framework with two metrics: the Deviation Composite Score (DCS) for spurious non-planarity and the Confusion Composite Score (CCS) for contextual instability.
  arXiv  Detail & Related papers  (2025-12-17T13:14:37Z)
• OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting [78.70702961852119]
  OracleGS reconciles generative completeness with regressive fidelity for sparse view Gaussian Splatting.<n>Our approach conditions the powerful generative prior on multi-view geometric evidence, filtering hallucinatory artifacts while preserving plausible completions in under-constrained regions.
  arXiv  Detail & Related papers  (2025-09-27T11:19:32Z)
• Distractor-free Generalizable 3D Gaussian Splatting [26.762275313390194]
  We present DGGS, a novel framework that addresses the previously unexplored challenge: $textbfDistractor-free Generalizable 3D Gaussian Splatting$ (3DGS)<n>It mitigates 3D inconsistency and training instability caused by distractor data in the cross-scenes generalizable train setting.<n>Our generalizable mask prediction even achieves an accuracy superior to existing scene-specific training methods.
  arXiv  Detail & Related papers  (2024-11-26T17:17:41Z)
• 3D-Prover: Diversity Driven Theorem Proving With Determinantal Point Processes [17.379356401253986]
  A key challenge in automated formal reasoning is the intractable search space, which grows exponentially with the depth of the proof.<n>We propose a novel filtering mechanism which leverages semantically diverse and high quality tactics.<n>We show that our approach leads to an increase in the overall proof rate, as well as a significant improvement in the tactic success rate, execution time and diversity.
  arXiv  Detail & Related papers  (2024-10-14T23:13:53Z)
• ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities [23.18281583681258]
  We propose a new task called 3D reasoning grounding and introduce a new benchmark ScanReason. ScanReason provides over 10K question-answer-location pairs from five reasoning types that require the synerization of reasoning and grounding. A chain-of-grounding mechanism is proposed to further boost the performance with interleaved reasoning and grounding steps during inference.
  arXiv  Detail & Related papers  (2024-07-01T17:59:35Z)
• 3D-QueryIS: A Query-based Framework for 3D Instance Segmentation [74.6998931386331]
  Previous methods for 3D instance segmentation often maintain inter-task dependencies and the tendency towards a lack of robustness. We propose a novel query-based method, termed as 3D-QueryIS, which is detector-free, semantic segmentation-free, and cluster-free. Our 3D-QueryIS is free from the accumulated errors caused by the inter-task dependencies.
  arXiv  Detail & Related papers  (2022-11-17T07:04:53Z)
• Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation [70.32536356351706]
  We introduce MRP-Net that constitutes a common deep network backbone with two output heads subscribing to two diverse configurations. We derive suitable measures to quantify prediction uncertainty at both pose and joint level. We present a comprehensive evaluation of the proposed approach and demonstrate state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-29T07:14:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.