REVIEW 10 cited by
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recent advances in deep thinking models have demonstrated remarkable reasoning capabilities on mathematical and coding tasks. However, their effectiveness in embodied domains which require continuous interaction with environments through image action interleaved trajectories remains largely -unexplored. We present Embodied Reasoner, a model that extends o1 style reasoning to interactive embodied search tasks. Unlike mathematical reasoning that relies primarily on logical deduction, embodied scenarios demand spatial understanding, temporal reasoning, and ongoing self-reflection based on interaction history. To address these challenges, we synthesize 9.3k coherent Observation-Thought-Action trajectories containing 64k interactive images and 90k diverse thinking processes (analysis, spatial reasoning, reflection, planning, and verification). We develop a three-stage training pipeline that progressively enhances the model's capabilities through imitation learning, self-exploration via rejection sampling, and self-correction through reflection tuning. The evaluation shows that our model significantly outperforms those advanced visual reasoning models, e.g., it exceeds OpenAI o1, o3-mini, and Claude-3.7 by +9\%, 24\%, and +13\%. Analysis reveals our model exhibits fewer repeated searches and logical inconsistencies, with particular advantages in complex long-horizon tasks. Real-world environments also show our superiority while exhibiting fewer repeated searches and logical inconsistency cases.
Forward citations
Cited by 10 Pith papers
-
What if? Emulative Simulation with World Models for Situated Reasoning
WanderDream supplies 15.8K panoramic mental-exploration videos and 158K QA pairs showing that world-model imagination measurably improves situated spatial reasoning without active exploration.
-
Any House Any Task: Scalable Long-Horizon Planning for Abstract Human Tasks
A reinforcement-trained LLM that decomposes abstract household requests into PDDL subgoals and solves them with a symbolic planner outperforms prompting and end-to-end planning baselines on long-horizon tasks.
-
Robix: A Unified Model for Robot Interaction, Reasoning and Planning
A three-stage-trained VLM unifies robot planning and dialogue, and beats commercial VLMs on the authors' interactive-task benchmarks.
-
RoboBrain 2.0 Technical Report
RoboBrain 2.0, a 7B/32B embodied vision-language model built on Qwen2.5-VL, reports state-of-the-art or near-top scores on several spatial and temporal reasoning benchmarks for robotics.
-
Reinforced Reasoning for Embodied Planning
An SFT-plus-GRPO recipe lifts a 7B VLM to 35.6 percent success on EB-ALFRED versus 22.0 for GPT-4o-mini and 33.7 for Qwen2.5-VL-72B, with smaller but consistent gains on unseen EB-Habitat.
-
VistaVLA: Geometry- and Semantic-Aware 3D Gaussian-Grounded VLA for Robotic Manipulation
VistaVLA lifts multi-view vision-language features into 3D Gaussians, compresses them 99% via Merge-then-Query, and improves real-robot manipulation success by ~23% over baselines.
-
RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning
A 3B VLM trained with SFT plus GRPO and an LCS-based reward reaches 55.3% on EmbodiedBench's EB-ALFRED, beating GPT-4o-mini and the 7B REBP planner.
-
WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning
WeThink, a 120K-image QA dataset with AI-generated reasoning paths, combined with hybrid-reward reinforcement learning, improves a 7B vision-language model across 14 benchmarks.
-
ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models
ManipLVM-R1 applies RLVR with IoU and trajectory-distance rewards to train a 3B VLM for affordance perception and trajectory prediction, claiming better performance and generalization than SFT on 50% of the data.
-
Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models
A survey-style position paper claims that reinforcement fine-tuning powers reasoning in multimodal LLMs, summarizing over a hundred recent works and proposing five future research directions.
Discussion (0). Sign in to comment.