GSR: Learning Structured Reasoning for Embodied Manipulation

• URL: http://arxiv.org/abs/2602.01693v1
• Date: Mon, 02 Feb 2026 06:07:42 GMT
• Title: GSR: Learning Structured Reasoning for Embodied Manipulation
• Abstract summary: Grounded Scene-graph Reasoning (GSR) is a structured reasoning paradigm that explicitly models world-state evolution as transitions over semantically grounded scene graphs.<n>GSR enables explicit reasoning about action preconditions, consequences, and goal satisfaction in a physically grounded space.
• Score: 10.756456261056867
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite rapid progress, embodied agents still struggle with long-horizon manipulation that requires maintaining spatial consistency, causal dependencies, and goal constraints. A key limitation of existing approaches is that task reasoning is implicitly embedded in high-dimensional latent representations, making it challenging to separate task structure from perceptual variability. We introduce Grounded Scene-graph Reasoning (GSR), a structured reasoning paradigm that explicitly models world-state evolution as transitions over semantically grounded scene graphs. By reasoning step-wise over object states and spatial relations, rather than directly mapping perception to actions, GSR enables explicit reasoning about action preconditions, consequences, and goal satisfaction in a physically grounded space. To support learning such reasoning, we construct Manip-Cognition-1.6M, a large-scale dataset that jointly supervises world understanding, action planning, and goal interpretation. Extensive evaluations across RLBench, LIBERO, GSR-benchmark, and real-world robotic tasks show that GSR significantly improves zero-shot generalization and long-horizon task completion over prompting-based baselines. These results highlight explicit world-state representations as a key inductive bias for scalable embodied reasoning.

Related papers

• Towards Generalizable Visually Grounded Exploration of Household Devices [74.66117923766632]
  Key bottleneck of realizing general autonomous embodied agents lies in Generalizable Visually Grounded Exploration.<n>We introduce VGEBench, a benchmark designed to evaluate the generalizable visually grounded exploration capabilities of Vision-Language Models.<n>Unlike static datasets, we construct a Logic-Driven State Machine framework. This framework simulates multi-turn interaction loops, compelling agents to achieve goals by active visual perception and feedback-driven correction.
  arXiv  Detail & Related papers  (2026-09-01T07:42:45Z)
• Towards Predictive, Aligned, and Scalable Robot Learning [11.830982964522605]
  We introduce Lumo-2, a latent world-action model that generates actions by reasoning over world dynamics in latent space.<n>We study latent world modelling and modality alignment, analyzing their roles in scaling laws and out-of-distribution generalization.<n>Results show that Lumo-2 consistently outperforms strong vision-language-action (VLA) and world-action model (WAM) baselines.
  arXiv  Detail & Related papers  (2026-07-13T08:53:34Z)
• RoBoSR: Structured Scene Representations for Embodied Robotic Reasoning [14.955041656490849]
  We introduce RoBoSR, an intermediate structural representation that formulates manipulation as step-wise state transitions.<n>By modeling object states and their spatial relations at the perception-action interface, RoBoSR disentangles high-level task reasoning from raw inputs.<n>We construct Manip-Cognition-1.6M, an open-world dataset that jointly supervises scene understanding, instruction interpretation, and subtask planning.
  arXiv  Detail & Related papers  (2026-06-23T09:24:52Z)
• ThinkingVLA: Interleaved Vision and Language Reasoning for Robotic Manipulation [71.69632267962993]
  We argue that manipulation planning naturally decomposes into prediction, anticipating the next visual state, and inverse dynamics.<n>We propose textbfThinkingVLA, a generative model that realizes this decomposition within a unified Mixture-of-Transformers architecture.<n>Experiments on simulation and real-world benchmarks demonstrate that ThinkingVLA consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-06-16T13:45:17Z)
• PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations [66.94988600664574]
  We present textbfPRTS (textbfPrimitive textbfReasoning and textbfTasking textbfSystem), a VLA foundation model that reformulates pretraining through Goal-Conditioned Reinforcement Learning.
  arXiv  Detail & Related papers  (2026-04-30T06:14:02Z)
• From Perception to Planning: Evolving Ego-Centric Task-Oriented Spatiotemporal Reasoning via Curriculum Learning [79.65573577667944]
  We present EgoTSR, a curriculum-based framework for learning task-basedtemporal reasoning.<n>EgoTSR is built on the premise embodied reasoning should evolve from explicit spatial understanding to task-state assessment.<n>Experiments demonstrate that EgoTSR effectively eliminates biases, achieving 92.4% accuracy on long-horizon logical reasoning tasks.
  arXiv  Detail & Related papers  (2026-04-12T08:14:49Z)
• Affordance-Graphed Task Worlds: Self-Evolving Task Generation for Scalable Embodied Learning [38.10198732103412]
  Affordance-Graphed Task Worlds (AGT-World) is a framework that autonomously constructs interactive simulated environments and corresponding robot task policies.<n>Unlike methods relying on random proposals or static replication, AGT-World formalizes the task space as a structured graph.<n>Our method significantly outperforms in success rates and generalization, achieving a self-improving cycle of proposal, execution, and correction for scalable robot learning.
  arXiv  Detail & Related papers  (2026-02-12T15:23:45Z)
• EscherVerse: An Open World Benchmark and Dataset for Teleo-Spatial Intelligence with Physical-Dynamic and Intent-Driven Understanding [56.89359230139883]
  We introduce Teleo-Spatial Intelligence (TSI), a new paradigm that unifies two critical pillars: Physical-Dynamic Reasoning and Intent-Driven Reasoning.<n>We present EscherVerse, consisting of a large-scale, open-world benchmark (Escher-Bench), a dataset (Escher-35k), and models (Escher series)<n>It is the first benchmark to systematically assess Intent-Driven Reasoning, challenging models to connect physical events to their underlying human purposes.
  arXiv  Detail & Related papers  (2026-01-04T14:42:39Z)
• Executable Analytic Concepts as the Missing Link Between VLM Insight and Precise Manipulation [70.8381970762877]
  Vision-Language Models (VLMs) have demonstrated remarkable capabilities in semantic reasoning and task planning.<n>We introduce GRACE, a novel framework that grounds VLM-based reasoning through executable analytic concepts.<n>G GRACE provides a unified and interpretable interface between high-level instruction understanding and low-level robot control.
  arXiv  Detail & Related papers  (2025-10-09T09:08:33Z)
• Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Models [8.021952962029165]
  Vision-Language Models (VLMs) in remote sensing often fail at complex analytical tasks.<n>We introduce the Perceptually-Grounded Geospatial Chain-of-Thought (Geo-CoT)<n>Geo-CoT is a framework that models remote sensing analysis as a verifiable, multi-step process.
  arXiv  Detail & Related papers  (2025-09-26T11:34:42Z)
• Reinforcing Video Reasoning Segmentation to Think Before It Segments [67.5703457389657]
  We introduce Veason-R1, a specialized LVLM for video reasoning segmentation.<n>Veason-R1 is trained through Group Relative Policy Optimization (O) augmented with Chain-of-Thought trajectories.<n>We incorporate a holistic reward mechanism that enhances spatial alignment and temporal consistency.<n>Veason-R1 achieves state-of-the-art performance on multiple benchmarks, surpassing prior art by significant margins.
  arXiv  Detail & Related papers  (2025-08-15T15:34:56Z)
• Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning [96.01617809845396]
  Ground-R1 is a reinforcement learning framework that enables grounded visual reasoning without requiring explicit evidence or rationale annotations.<n>Ground-R1 achieves superior performance and exhibits emergent cognitive behaviors such as uncertainty awareness, spatial perception, and iterative refinement.
  arXiv  Detail & Related papers  (2025-05-26T17:51:47Z)
• EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks [24.41705039390567]
  EmbodiedVSR (Embodied Visual Spatial Reasoning) is a novel framework that integrates dynamic scene graph-guided Chain-of-Thought (CoT) reasoning.<n>Our method enables zero-shot spatial reasoning without task-specific fine-tuning.<n>Experiments demonstrate that our framework significantly outperforms existing MLLM-based methods in accuracy and reasoning coherence.
  arXiv  Detail & Related papers  (2025-03-14T05:06:07Z)
• Grounded Situation Recognition [56.18102368133022]
  We introduce Grounded Situation Recognition (GSR), a task that requires producing structured semantic summaries of images. GSR presents important technical challenges: identifying semantic saliency, categorizing and localizing a large and diverse set of entities. We show initial findings on three exciting future directions enabled by our models: conditional querying, visual chaining, and grounded semantic aware image retrieval.
  arXiv  Detail & Related papers  (2020-03-26T17:57:52Z)

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.