Egocentric world models predict first-person observations conditioned on an agent's actions, but most focus on a single agent. Real embodied settings often involve multiple agents that act and interact within a shared environment. Existing multi-agent world models rely on coarse actions like locomotion, camera control, or discrete commands, leaving fine-grained embodied interactions underexplored. We formulate multi-agent egocentric world modeling as synchronized ego-stream generation for multiple agents interacting through fine-grained actions in a shared world. This requires cross-view action consistency, shared-environment consistency, and consistent propagation of interaction-induced state updates. We propose Multi-agent Egocentric World Model (ME-World), which jointly denoises multiple ego streams in a shared token sequence, conditions each stream on all agents' target-view poses, and grounds generation with shared environment memory. We train and evaluate on real and synthetic multi-agent data and introduce shared-world consistency metrics for environment, update, and identity consistency. Experiments show ME-World improves shared-world consistency, action control, identity preservation, and video quality over existing methods.

kaist-ai

Dahyun Chung

Siyoon Jin

Hyunwook Choi

Honggyu An

Junyoung Seo

Hyunsung Kim

Seung Wook Kim

Seungryong Kim

enrue1893

Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction

Egocentric world models predict first-person observations conditioned on an agent's actions, but most focus on a single agent. Real embodied settings often involve multiple agents that act and interact within a shared environment.

Realistic environment replicas are increasingly valuable for training and evaluating LLM agents, yet the original systems may be inaccessible or impractical to reproduce. We explore agentic language world modeling: rather than rebuilding an executable environment, a world model agent serves as the environment for a task agent and supports faithful and stateful simulation. We instantiate this paradigm with Trace2Env, a learning-free framework for settings where the original system is unavailable but historical interaction traces remain accessible. Trace2Env reconstructs these traces into a reusable environment worldbook containing environment schemas, grounded evidence, and induced behavioral knowledge. At runtime, the world model agent actively consults the worldbook together with persistent episodic state to infer each action's observation and lasting state effects. Across nine environments, Trace2Env improves both next-observation fidelity and long-horizon interaction consistency over conventional prompt-based LWMs. In multi-turn interaction, task agent actions generated against Trace2Env remain valid more often when replayed in the real environment, indicating that its simulated dynamics better preserve the consequences of earlier actions across successive turns. These results establish agentic language world modeling as an alternative direction for building realistic environment replicas without reconstructing the original executable system.

nanyang-technological-university-singapore

Quanyu Long

Quanyu001

Xiao Chen

chrisCCC

Jianda Chen

Haozhen Zhang

Qisheng Hu

Jianzhu Bao

Wenya Wang

From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation

Realistic environment replicas are increasingly valuable for training and evaluating LLM agents, yet the original systems may be inaccessible or impractical to reproduce. We explore agentic language world modeling: rather than rebuilding an executable environment, a world model agent serves as the environment for a task agent and supports faithful and stateful simulation.

General-purpose service robots need navigation systems that can handle diverse human requests in unfamiliar environments, combining task generality with scene generality. Some existing methods fine-tune multimodal large language models (MLLMs) to predict navigation actions, making their behavior dependent on the coverage of navigation training data and potentially limiting generalization to new requests and environments. Our key insight is to let the MLLM focus on interpreting requests, understanding scenes, and making decisions while preserving its general-purpose capabilities and delegating motion execution to navigation tools. To realize this idea, we introduce SuperNav, which equips a pretrained MLLM with a specialized agent harness without navigation-specific fine-tuning of the MLLM. Our harness supports these decisions with Navigation Skills, agent-oriented Tools for physical interaction, and task-progress and context management. A unified visual-point interface connects decision-making to motion by allowing the model to specify destinations directly in images and revise its decisions from execution feedback. Together, these components support sustained navigation across different task requirements and environments. SuperNav outperforms four evaluated baselines on instance-level, multi-object, and demand-driven tasks. Category-level evaluation on HM3D and deployment on a real quadruped robot further demonstrate its applicability across environments. Project Page: https://zju3dv.github.io/SuperNav/

zju3dv

Jinkai Zhang

the0xka1

Jingyi Xu

Yuanhong Yu

yyh929

Jiarui Guo

Ruizhen Hu

Hujun Bao

Xiaowei Zhou

Sida Peng

SuperNav: An Agentic Navigation System for Any Task in Any Scene

General-purpose service robots need navigation systems that can handle diverse human requests in unfamiliar environments, combining task generality with scene generality. Some existing methods fine-tune multimodal large language models (MLLMs) to predict navigation actions, making their behavior dependent on the coverage of navigation training data and potentially limiting generalization to new requests and environments.

We study robotic in-context learning (ICL), an emerging paradigm that enables robots to infer and execute tasks from visual demonstrations. Despite its growing promise, the problem itself remains under-defined: a visual demonstration simultaneously conveys action trajectories, object semantics, manipulation affordances, spatial relations, and task goals, making it unclear what information the robot is actually expected to follow. In this work, we first provide a clear problem definition of robot ICL that explicitly defines its learning target and resolves this fundamental prompt ambiguity. Building on this definition, we develop a minimalist and reproducible ICL framework (SimpleICL) with a visual prompt encoder and a low-cost data collection protocol. Without massive pre-training or specialized data infrastructure, our framework achieves strong performance in both simulation and real-world environments. Extensive experiments further reveal several key properties of robot ICL, including action, semantic, composition, and affordance discrimination. We will fully open-source our data and training pipeline to facilitate systematic and reproducible research on robot ICL. The project page can be found at https://simpleicl.github.io/simpleicl.

Minxing Li

Minghao Han

Weizhi Zhao

Hanwen Wang

gothicwhw

Xiangshuo Liu

Shuyao Shang

Jingxiang Zhou

Mingchao Sun

Hongyu Pan

Mu Xu

Yu Liu

Lue Fan

Zhaoxiang Zhang

In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks

We study robotic in-context learning (ICL), an emerging paradigm that enables robots to infer and execute tasks from visual demonstrations. Despite its growing promise, the problem itself remains under-defined: a visual demonstration simultaneously conveys action trajectories, object semantics, manipulation affordances, spatial relations, and task goals, making it unclear what information the robot is actually expected to follow.

Large language model (LLM) routing distributes inference work across different models, advancing the cost-quality Pareto frontier of LLM serving. While coarse-grained routing at the session or query level has been widely adopted in production systems, recent algorithmic work shows that fine-grained token-level routing can yield substantial efficiency and quality gains. However, efficiently serving token-level routed inference poses significant challenges to existing systems. Built on single-LLM assumptions, current systems suffer from severe step desynchronization and frequent batch admission delays under token-level routing, and they also impose high implementation complexity on developers. To address these challenges, we design TokenRouter, an efficient and developer-friendly serving system for token-level routed LLM inference. TokenRouter follows the principle of request-centric programming, model-centric execution: developers describe routing logic from the perspective of a single request, while the runtime launches a subserver for each LLM and dispatches requests asynchronously. Each subserver employs a delayed-batching scheduler, whose optimal hyperparameters are derived from a mathematical throughput model of the system. Across diverse routing algorithms, workloads, and model pairs, TokenRouter achieves 2.01-64.15x higher decoding throughput than existing systems, substantially advancing the serving efficiency of token-level LLM routing. Our code is available at https://github.com/thu-nics/TokenRouter.

nics-efc

Tianyu Fu

fuvty

Tengxuan Liu

MX05

Ruoxi Wang

PuppetW

Yixin Dong

Yi Ge

Yichen You

youyc22

Yu Wang

TokenRouter: Efficient Serving System for Token-Level LLM Routing

Large language model (LLM) routing distributes inference work across different models, advancing the cost-quality Pareto frontier of LLM serving. While coarse-grained routing at the session or query level has been widely adopted in production systems, recent algorithmic work shows that fine-grained token-level routing can yield substantial efficiency and quality gains.

Large language models are informing decisions with ever-higher stakes. As the consequences of their errors grow, a central question becomes harder to ignore: how much can we trust an individual answer? Yet recognizing when to defer remains difficult because language models can present incorrect conclusions with fluent explanations and an authoritative tone. Uncertainty quantification seeks to address this disconnect by estimating the reliability of individual predictions. However, many existing methods require repeated generations or separately trained components, and their scalar estimates do not reveal where uncertainty arises or how it evolves during reasoning. Recent work has also shown that generation length can be strongly associated with uncertainty estimates and correctness, raising the question of how much of an estimator's predictive power comes from uncertainty-specific information rather than output length alone. Mechanistic interpretability offers a way to address these limitations by connecting human-interpretable concepts to intermediate model states. Building on this capability, we introduce the U-Space, a low-dimensional subspace that makes a model's evolving uncertainty measurable and interpretable. We identify semantic anchors for doubt and certainty, map their unembedding directions back into the residual space, and combine their contrasts into an orthogonal basis. The U-Lens projects each token state onto these basis vectors, yielding an interpretable token-level uncertainty map that can be inspected directly or aggregated into a scalar uncertainty score. Our approach requires no correctness labels, repeated generations, or training. Across reasoning benchmarks, its confidence score outperforms established baselines under both standard and length-controlled evaluation and transfers more reliably than supervised estimators. Code: https://github.com/s2labres/U-Space.

MAI-Lab

Tobias Braun

tbrx

Nils Loose

loose-bits

Alexander Herzog

Virginia Ceccatelli

virginiaceccatelli

Marcus Rohrbach

Thomas Eisenbarth

Lorenzo Cavallaro

U-Space: Uncovering When and Why Uncertainty Arises in Language Models

Large language models are informing decisions with ever-higher stakes. As the consequences of their errors grow, a central question becomes harder to ignore: how much can we trust an individual answer?

Reinforcement learning (RL) is the central training paradigm for advancing large foundation models towards self-improvement. This report introduces the MiMo-V2.6 series, an omni-modal family that pushes the frontier of model intelligence by scaling RL compute. Prior to RL, we conduct mid-training on a broad multimodal corpus to provide ample exploration space, and build a solid infrastructure on the pretrained hybrid-SWA architecture to support subsequent scale-up. We scale RL compute along three dimensions: (1) larger batches and higher throughput, with an asynchronous training that consumes 1,568 samples and 2.7-3.7B tokens per step at context lengths of up to 1M; (2) more diverse and complex environments, spanning code, general, visual, and cyber domains under a mixture of agent harnesses; and (3) more grader compute, via groupwise agentic grading that yields more accurate reward signals for long-horizon tasks and steers the model towards shorter, more token-efficient solutions. To keep training stable at scale, we freeze the MoE router and establish a multi-layer defense against reward hacking. We further build infrastructure for mixed-task agentic RL, including a unified trajectory representation, high-concurrency multi-framework rollout, decoupled control and data planes, and training-inference consistency. We open-source the training dynamics, RL environments, and RL framework to facilitate reproduction and further research on scaled RL and model self-improvement.

XiaomiMiMo

Core Team

Zongming Qiao

Ziyue Hua

Zirui Ou

Zihao Yue

Zihan Jiang

Zhuo Huang

Zhiyang Chen

Zhixian Zheng

Zhipeng Xu

Zhengrui Ma

Yuyang Hu

Yuhang Dong

Yuechen Zhang

Yudong Wang

Yuanxin Liu

Yixin Yang

Yishuo Cai

Yikai Zhao

Yihan Yan

Yifan Zhang

Yifan Song

Xiyu Wei

Xing Zhang

Xin Zhang

Xiaoqian Liu

Xiaodong Ji

Xiangwei Deng

Xueyu Guo

Wenhan Ma

Weimin Xiong

Weikun Wang

kunwww

Weiji Zhuang

Shuo Liu

Shuhuai Ren

Shuhao Gu

Shimao Chen

Shijie Cao

Shihua Yu

Shicheng Li

Shengjie Zhou

Shaolei Zhang

Rang Li

lirang04

Qiying Wang

Qingkai Fang

Qianli Chen

Minzheng Wang

Liwen Wang

Linli Yao

Linghao Zhang

Liangyu Cheng

Liang Zhao

Lei Li

Jinhao Dong

Jinyu Xiang

XiangJinYu

Jianyu Wei

Jiangshan Duo

Huaqiu Liu

Huanjie Fan

Hongyi Guan

Hongshen Xu

Hao Tian

Hanyu Li

Hailin Zhang

Gang Wang

Fuli Luo

Feng Wei

Dong Zhang

Dawei Zhu

Chiheng Lou

Chenhong He

Chenhao He

Chenghua Liu

Bowen Ye

Ymiracle

Bowen Shen

Boshen Xu

Bo Yang

Bingquan Xia

Bangjun Xiao

Baixuan Xu

Zhouxiang Mao

Zhiyang Zhang

Zhixiang Xu

Zhenru Lin

Zhengju Tang

Zhaojun Huang

Yuzhe Weng

Yuxing Xiang

Yuxiao Li

ly-xxx

Yuheng Yang

lukayang432

Yuhang Wang

Yuchen Liu

Yuanyuan Tian

Yuanliang Dong

Yu Cheng

Yongzhe He

Yongshun Liang

Yong Wang

Yiyan Wang

Yitian Gong

fdugyt

whatseeker

MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement

Reinforcement learning (RL) is the central training paradigm for advancing large foundation models towards self-improvement. This report introduces the MiMo-V2.6 series, an omni-modal family that pushes the frontier of model intelligence by scaling RL compute.

Recent 3D world models generate photorealistic, explorable scenes that remain frozen in time. OuroWorld is a mask-free framework that turns any static 3D Gaussian Splatting scene into a 3D cinemagraph: a dynamic scene with vivid, diverse motion looping seamlessly from any viewpoint. A vision-language model infers plausible dynamics and guides a video model to synthesize a reference video, which we lift and complete into multi-view videos. To learn from this imperfect supervision, we propose Inconsistency-Robust Periodic 4DGS: a Fourier-series deformation field guarantees looping by construction, while a Grounded Drift Field anchored at the reference view absorbs cross-view inconsistency. Unlike prior Eulerian methods limited to fluid-like motion, we capture general deformation, object motion, and illumination change. We introduce a ground-truth-free evaluation covering vividness, naturalness, loop seam coherence, and scene quality. On 39 reconstructed and generated scenes, OuroWorld outperforms all baselines and wins 70.8%-99.0% of user-study comparisons. Project page: https://ouroworld.userwei.com

AlayaLab

You-Zhe Xie

OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs

Recent 3D world models generate photorealistic, explorable scenes that remain frozen in time. OuroWorld is a mask-free framework that turns any static 3D Gaussian Splatting scene into a 3D cinemagraph: a dynamic scene with vivid, diverse motion looping seamlessly from any viewpoint.

AI Research Made Simple

Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction

From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation

SuperNav: An Agentic Navigation System for Any Task in Any Scene

In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks

TokenRouter: Efficient Serving System for Token-Level LLM Routing

U-Space: Uncovering When and Why Uncertainty Arises in Language Models

MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement

OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs

Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching

REMORY: Learning Residual Memory for Context Compaction

Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?

AgentGarten: Code Worlds for Evolving Agents