Papers

Social Humanoid: Socially Responsive Human-Humanoid Interaction

Humanoid robots are typically trained as solitary agents, leaving them unable to coordinate physically with human partners who naturally anticipate and adjust to one another. To bridge this gap, we present Social Humanoid, a hierarchical system that generates and executes socially responsive whole-body motion on a 29-DoF Unitree G1 conditioned on a human partner's motion. Its high-level policy performs flexible sequence modeling of human and humanoid motion through a shared tokenized representation, generating reactive humanoid motion and anticipating the partner's motion when they are occluded, while a low-level whole-body tracking controller executes the generated motion on the robot. To train the system, we introduce a two-phase adaptive retargeting procedure that retargets one interaction partner to the robot while morphing the other partner to preserve contact dynamics, reachability, and relative body scale. We apply this procedure across five motion-capture datasets to produce a new Human-Humanoid Interaction (HHI) benchmark of 260 hours of human-humanoid interactions. Our results demonstrate that Social Humanoid produces coordinated, human-aligned behavior across diverse interaction types in simulation and the real world. Project page: https://von31.github.io/social-humanoid/

HumanoidHuman-humanoid interaction

Vongani H. Maluleke, James Ni, Kie Horiuchi · 45 views · Nov 5, 2026

OmniBrain-0: A Unified Agentic Model for Embodied Intelligence

General-purpose embodied intelligence requires robots to coordinate diverse skills over long horizons, track task progress, and recover from failures. Specialist policies alone do not ensure task-level reliability, while powerful multimodal agents rely on costly reasoning and external experience that compact models struggle to reproduce. We introduce OmniBrain-0, a lightweight unified embodied agent that coordinates manipulation and navigation through a shared high-level decision model, integrating task understanding, planning, progress tracking, and feedback-driven recovery. Our progressive training framework combines embodied pretraining, domain-specialized agent distillation, and multi-teacher on-policy distillation (MOPD). It distills powerful teachers' interaction experience into manipulation and navigation experts, then consolidates their decision capabilities into OmniBrain-0. Unification therefore occurs within the learned decision model rather than only at the tool interface. We further introduce Rubric-Guided Recursive Self-Improvement (RSI), a data flywheel in which a Meta-Agent turns execution evidence into refined rubrics, step-level reminders, and verified trajectories for domain-expert updates before their reconsolidation into OmniBrain-0 through MOPD. We evaluate OmniBrain-0 on LIBERO-Pro, LIBERO-Plus, RoboCasa365, RoboTwin 2.0, and R2R-CE Val-Unseen, as well as multiple real-world manipulation tasks. OmniBrain-0 combines strong cross-domain task performance with substantially lower inference and execution overhead than its closed-source teacher, demonstrating efficient transfer and consolidation of embodied capabilities into a compact unified agent.

Embodied AIVLA

Xiaomi Embodied Intelligence Team, Yuechen Luo, Chong He · 81 views · Oct 26, 2026

One Scan is Enough: Demonstration-Free Adaptation for Language-Guided Navigation

Deploying a language-guided navigation policy in a new building usually means watching it fail. Public-benchmark VLAs degrade scene by scene as layout, appearance, and language drift, and the standard fix of teleoperating fresh trajectories on site does not scale. We replace human demonstration with a single brief iPhone scan. Scan2Instruction compiles that scan into a complete training environment, automatically synthesizing executable navigation episodes with grounded instructions. PRPT-KS then adapts the policy through a closed-form Pareto utility read directly off the reconstructed scene, with no learned critic and no human labels. Across five real environments, the two designs together drive our RealNav to an 85% real-robot success rate, compared with 49% for a RealNav baseline post-trained on human demonstrations, and still achieve 82% in unscanned regions of the same buildings, compared with 41% for the same baseline. Our work turns demonstration-free scene adaptation for language-guided navigation from an aspiration into a working reality.

Vision-language navigationRobot navigation

Zhuoyuan Yu, Yuxing Long, Du Wang · 52 views · Oct 24, 2026

GRAFT: Grounded and Efficient Online Reinforcement Adaptation for Fine-Grained Robot Manipulation

Pretrained vision-language-action (VLA) policies provide strong priors for robot manipulation, yet adapting them online to fine-grained biomedical tasks remains challenging. Task success often hinges on subtle, view-dependent visual cues, while task-level rewards provide little guidance about which regions matter, making it difficult to learn task-relevant visual grounding from limited real-robot interaction. Online adaptation is further constrained by the computational cost of VLA inference and replay-based updates. We introduce GRAFT (Grounded Reinforcement Adaptation for Fast Task Learning), a framework for efficient online VLA adaptation through grounded perception. GRAFT uses region-level supervision to learn view-specific visual anchors that focus perception on task-relevant local cues without requiring region proposals at deployment. It further combines single-step action generation with cached visual-language prefix reuse to accelerate online learning. Across four biomedical manipulation tasks, GRAFT improves success rates by 32.5 percentage points under matched adaptation budgets, while reducing the computational overhead of online policy updates.

VLARobot Manipulation

Yibo Qiu, Haoliang Ye, Shu'ang Sun · 77 views · Aug 27, 2026

RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments

RobotWorld introduces a cross-embodiment robot-use benchmark spanning 84 tasks and evaluates whether multimodal agents can convert perception and computation into verifier-confirmed physical execution.

Robot BenchmarkEmbodied AI

Zhiqin Yang, Chenxin Li, Xiaomeng Hu · 70 views · Oct 7, 2026

Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents

The paper introduces Hybrid Computer Use (HCU), a unified agent interface that combines code and command-line interaction, accessibility-tree semantics, and screenshot-based mouse and keyboard control in one context. Compact observations, batched action execution of up to 64 steps, wait steps, post-action diffs, and cross-channel goal and layout guards reduce round trips and prevent stale-input actions. HCU improves task success or interaction efficiency across OSWorld 2.0, OSWorld 1.0, WeaveBench, macOS, and Windows Agent Arena.

Agent HarnessComputer Use

Haoqing Wang, Xiaoyi Zhang, Sicheng Fan · 61 views · Oct 30, 2026

ServerBench: How can your coding agents design specialized LLM serving systems?

ServerBench evaluates whether coding agents can design complete specialized LLM serving systems through stateful coding-session replay, latency-qualified dollars-per-dollar scoring, and independent verification.

LLMLLM Serving

Xinrui Zhong, Zhiming Wang, Yongqi Liu · 69 views · Nov 4, 2026

SERF: Spatiotemporal Environment and Robot Feature Map for Long-Horizon Mobile Manipulation

SERF represents the environment and the articulated robot body as neural points in one shared latent space and updates them online. Environment points follow object-level rigid registration, while robot surface points are posed by forward kinematics. A shared residual decoder maps local point features to DINOv3 patch embeddings, and a two-stage Point Transformer produces eight map tokens from three robot-centered radii, both end effectors, robot-only, environment-only, and global branches. These tokens condition a VLA policy together with images, proprioception, and language. Across three long-horizon BEHAVIOR-1K tasks, SERF raises average progress from 44.0% for fine-tuned PI0.5 to 58.7%, and the paper also reports gains when labels and base poses are estimated onboard, when object-drop recovery is required, and in unvisited regions.

VLAMobile Manipulation

Sunghwan Kim, Byeonghyun Pak, Kehan Long · 70 views · Jun 11, 2026

Reinforcement Learning Enables Scaling Generalist Robot Policy Improvement

The introduction of generalist robot policies has enabled a single, large model to learn to perform a variety of tasks from a vast pre-training corpus. While these models often exhibit powerful zero-shot generalization capabilities, they typically require an adaptation phase to achieve sufficient performance in deployment. Iterated self-improvement via reinforcement learning (RL) has demonstrated promise in enabling this adaptation, yet such approaches have been largely explored in single-task settings - where the goal is to simply improve on a narrow deployment task - which lies in stark contrast to the multi-task capabilities of the base policy. In this work we ask whether generalist robot policies are capable of multi-task, generalist improvement in deployment - targeting many diverse tasks simultaneously - and what algorithmic recipe enables this. To answer this question, we first develop a set of structured evaluations to test generalist improvement capabilities, and systematically evaluate algorithmic and practical design choices regarding value estimation, policy extraction and resource allocation. We show that not only can generalist policies be improved online across diverse tasks, but that the right recipe can enable generalization and increase performance on tasks not considered during online training. We characterize when this generalization occurs and show that both the training task distribution and the use of value-based RL are critical. To the best of our knowledge, this is among the first evidence for online generalist improvement for robot foundation models.

Vision-language-action (VLA)Reinforcement Learning

Michal Korniak, Marco Bagatella, Ralf Römer · 69 views · Nov 4, 2026

Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systems

Route Anything unifies model and policy routing across text, images, video, speech, code agents, and robot manipulation. Its 25-benchmark trajectory matrix shows 5.38 points of per-input oracle headroom over the best fixed candidate; learned routers gain 0.30 points overall, while priced routes raise efficiency by 8.82x on average and a certified zero-loss code route holds its quality floor in all 200 splits.

LLMModel Routing

Pengfei Zhou, Yixing Ma, Hexin Wang · 93 views · Nov 3, 2026

Future Representation Distillation for Imagination-Free World Action Models

DreamFree turns a pretrained video diffusion model into a predictive visual encoder. A frozen teacher observes current and future frames, while a student predicts the teacher future representation from the current observation alone, so deployment avoids future-video denoising. Two-stage training combines future representation distillation with native flow matching, then learns an action readout and an action DiT. The 14B model reaches strong results on LIBERO, RoboCasa-Kitchen, and real DROID manipulation while running closed-loop control at 11 Hz, 17.8 times faster than DreamZero.

World-action modelsVideo Diffusion

Jaehyeong Jo, Sangwon Jang, Sihyun Yu · 86 views · Nov 3, 2026

HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness

Embodied navigation requires an agent to ground instructions or object goals in spatial observations and turn plans into execution. HarnessVLN is a zero-shot, training-free agent harness that coordinates perception, hierarchical event memory, a persistent spatiotemporal graph, and navigation tools through a shared interface. Before dispatch, the harness checks evidential support, geometric feasibility, and subgoal consistency; structured execution feedback then updates task progress, spatial evidence, and failure records for subsequent planning, recovery, and stopping. HarnessVLN reaches success rates of 60.8% on R2R, 53.9% on RxR, 76.0% on HM3D-v2, and 59.3% on HM3D-OVON, outperforming the training-free methods compared in the paper. Three real-world scenarios on an AgiBot A3U humanoid demonstrate deployment feasibility across both navigation families. Project page: https://agibot-harnessvln.netlify.app/.

Vision-language navigationEmbodied AI

Yang Chen, Lirong Che, Zhenyu Huang · 104 views · Sep 14, 2026

As an Amazon Associate, we earn from qualifying purchases.