Applied & Human-Centered · Computer Science & AI
Robotics
The newest papers in Robotics that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
4,418 papers, from 4 September 2026 to 5 November 2026: 4,418 arXiv preprints.
Get the few papers worth your time in Robotics every morning.
Follow Robotics and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 142
UMR: Universal Manipulation Representation
General-purpose embodied manipulation hinges on a unified action representation that generalizes across embodiments and scales readily.RoboICL: Embodied In-Context Learning with GPT-6 Astra
General-purpose vision-language models offer a promising way to zero-shot robot control: \gptastra{} excels at open-ended and language- or image-conditioned manipulation but remains substantially…SAGE: Symbolic Action-Gating and Editing for LLM Task Planners
Large language models (LLMs) are now the default cognitive core of embodied household agents, yet the plans they emit are rarely checked against a grounded model of the environment before execution…Bayesian Active Learning for Intent Disambiguation in Interactive Robot Planning
Interactive robot planning requires robots to infer and execute human intentions from natural language instructions that are often ambiguous, incomplete, or underspecified.NavHarness: Towards Lifelong Embodied Navigation
Frontier models can now perform well on individual embodied navigation tasks through multi-round multimodal reasoning with simple tools.Dexterous Tactile World Model
World models for manipulation are typically trained from video, yet the events that determine how manipulation unfolds, such as making and releasing contact, are difficult to observe visually and…TLC-DiT: Task-Aligned Local Visual Conditioning for Robust Multitask Robot Manipulation
Language-conditioned robot policies have made clear progress in multitask manipulation, but task-relevant local visual evidence usually stays hidden inside a visual backbone or attention layers.When World Models Lie: Adaptive Safety Analysis Under Wrong Imaginations
World models offer a powerful substrate for safety reasoning in high-dimensional robotic systems, but they are also fallible: their predictions can be biased, miscalibrated, or confidently wrong.Text-Vision Synergistic Token Caching: A Training-Free Framework for Efficient Vision-Language-Action Inference
Vision-Language-Action (VLA) models enable generalizable robotic control but remain computationally expensive.Predictive Semantic Safety: From Visual Physical Reasoning to Safety-Critical Control
Physical interactions can create future hazards that are not apparent from the robot's current geometric surroundings.FutureDuet: Decoupling Observation Access from Future Supervision in World Action Models
World Action Models (WAMs) augment robot action generation with future visual supervision.Emergence, Not Bandwidth: Physical Coupling and the Limits of Learned Multi-Agent Communication
Rate-limited multi-agent teams raise three questions the emergent-communication literature has answered only empirically: what an optimal message should encode, what compression costs over a…LRC-JEPA: Disentangling Dynamics and Residual Context for Efficient World Models
Compact JEPA world models enable efficient latent-space planning, but low-dimensional representation trained under reward-free self-supervision must encode both action-conditioned dynamics and…RoboIRGBench: Benchmarking Implicit Referential Grounding in Vision-Language-Action Models
Vision-Language-Action (VLA) models have shown strong capabilities in robotic manipulation, yet existing benchmarks typically assume that task-relevant information is explicitly specified in the…Contact-Aware Impedance Controller for Robot-Assisted Ultrasound Imaging
Safe robot-assisted ultrasound imaging requires a reliable controller able to detect and localize probe--tissue interaction.From Language to Task Maps: Compiling Semantic Relations While Preserving Task-Relevant Freedom
Natural-language manipulation instructions specify qualitative relations, whereas continuous controllers require state-evaluable task quantities, differentials, and completion conditions.From World Models to World Action Models: Rethinking Next-State Prediction
Predicting the next state is a core paradigm of World Models for modeling physical dynamics, emphasizing prediction fidelity.When the Score Becomes the Target: Rethinking Metric Validity in Autonomous Driving
Driving benchmark scores are increasingly used not only for evaluation but also as optimization targets.ARS: Agentic Reward System for Robot Learning
Progress reward modeling is the problem of estimating how a robot's behavior changes task progress over time.Trajectory-Safe Orienteering for Human-Robot Shared Environments
Orienteering problem (OP) has wide real-world applications and also great potential in human-robot collaboration.