Papersby GlyphWhat it shows
Action Reasoning Models (ARMs) integrate perception, planning, and control to enable adaptable and explainable robotic behavior, achieving superior performance across various tasks and settings.
By Jason Lee, Jiafei Duan, Haoquan Fang and 16 more · arXiv 2508.07917 · PDF · Code
UnverifiedHugging Face's summary; not yet checked by hand.
More from Ai2
All 7MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction3D point motion forecasting model predicts object trajectories from visual history and language goals, demonstrating superior performance on benchmarks and transferring effectively to robot manipulation and video generation tasks.
Ai216 citations53 upvotesRead →MolmoAct2: Action Reasoning Models for Real-world DeploymentA fully open robot action model, released with new datasets including 720 hours of two-arm teleoperation.Ai2100 citations355 upvotesRead →WildDet3D: Scaling Promptable 3D Detection in the WildA unified 3D object detection framework with a large-scale dataset enables open-world detection with multiple prompt types and geometric cue integration.Ai215 citations95 upvotesRead →TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for RoboticsTOPReward is a probabilistically grounded temporal value function that uses pretrained video Vision-Language Models to estimate robotic task progress through internal token logits, achieving superior performance in zero-shot evaluations across diverse real-world tasks.Ai243 citations26 upvotesRead →Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative ReasoningRD-VLA introduces a recurrent architecture for vision-language-action models that adapts computational depth through latent iterative refinement, achieving constant memory usage and improved task success rates.Ai221 citations71 upvotesRead →Olmo 3Olmo 3, a family of state-of-the-art fully-open language models at 7B and 32B parameter scales, excels in long-context reasoning, function calling, coding, instruction following, general chat, and knowledge recall.Ai237 upvotesRead →
Other reasoning papers
TopicChain-of-Thought Prompting Elicits Reasoning in Large Language ModelsAsking a model to write out its intermediate steps (chain of thought) sharply improves its math and logic answers.
Google23.8k citations16 upvotesRead →DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language ModelsDeepSeekMath 7B improves mathematical reasoning through enhanced data pre-training and Group Relative Policy Optimization, achieving high scores on MATH benchmark without external tools.
DeepSeek10.6k citations152 upvotesRead →DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement LearningReinforcement learning taught a model long step-by-step reasoning on par with OpenAI o1.DeepSeek5,972 citations458 upvotesRead →DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code IntelligenceDeepSeek-Coder-V2, a Mixture-of-Experts language model, excels in code-specific tasks by enhancing coding and mathematical reasoning capabilities while expanding language support and context length.DeepSeek530 citations73 upvotesRead →ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent PlanningThinkAct, a dual-system framework, uses reinforced visual latent planning to enable few-shot adaptation, long-horizon planning, and self-correction in embodied AI tasks by bridging high-level reasoning with low-level action execution.
NVIDIA192 citations43 upvotesRead →WebShaper: Agentically Data Synthesizing via Information-Seeking FormalizationWebShaper, a formalization-driven framework, synthesizes information-seeking datasets using set theory and Knowledge Projections to enhance reasoning structure and achieve top performance in open-sourced benchmarks.
Alibaba (Qwen)129 citations53 upvotesRead →
About this paper
- Venue
- IEEE International Conference on Robotics and Automation
- Citations
- 232, 31 influential · Semantic Scholar
- Upvotes
- 45 · Hugging Face
- Lab
- Ai2 · on Companies · on blogs · on labs · on Leaders · on Paydays · on problems · on Releases · on repos · on socials · on standards · on terms · on Titlewave
Changes
Influential citations rose from 26 to 31.
Citations rose from 208 to 232.
Influential citations rose from 25 to 26.
Citations rose from 199 to 208.
Influential citations rose from 22 to 25.
Citations rose from 187 to 199.
Citations rose from 185 to 187.
A first count of 22 influential citations.
A first count of 185 citations.
Found by the weekly Hugging Face scan; not yet checked by hand.