H.M. Qu

Xiaomi Robotics Team, Jun Guo, Piaopiao Jin et al.

We present Xiaomi-Robotics-1, a foundational vision-language-action (VLA) model capable of (1) following diverse language instructions to perform a wide range of mobile manipulation tasks in unseen environments out-of-the-box, and (2) efficiently adapting to novel downstream tasks with minimal fine-tuning data. We propose a two-stage training recipe consisting of pre-training and post-training. During pre-training, we imbue the model with broad and generalizable action-generation capabilities by training on over 100k hours of real-world manipulation trajectories collected via UMI devices. Crucially, we develop a scalable auto-labeling pipeline that annotates trajectory clips with natural languages describing scene state transitions, providing rich and precise conditioning for action learning. During post-training, we aim to align these capabilities with robot embodiments and imperative instructions that humans naturally use to prompt robots. Extensive experiments demonstrate strong scaling behavior. Xiaomi-Robotics-1 consistently improves with increased data scales and model sizes during pre-training. This scaling behavior directly transfers to post-training, where a stronger pre-training model yields better out-of-the-box real-robot performance in unseen environments. Furthermore, Xiaomi-Robotics-1 serves as a strong robot foundation policy that can be efficiently fine-tuned on complex, dexterous tasks with high data efficiency. Across multiple simulation benchmarks, Xiaomi-Robotics-1 outperforms state-of-the-art methods. Notably, it establishes a new state-of-the-art with a 57.6% success rate on RoboCasa365, surpassing the previous best of 46.6%. Furthermore, it achieves an average score of 20.07 on RoboDojo, significantly outperforming the prior state-of-the-art (13.07). Code and model checkpoints will be released. Project page: https://robotics.xiaomi.com/xiaomi-robotics-1.html

Zixin Chen, Peng Liu, Haobo Li et al.

Answering complex questions over long documents frequently requires integrating evidence that the source itself disperses naturally across distant passages. In an incident report, the operating condition, design flaw, and missed safety check that jointly explain a disaster may appear dozens of sections apart; in a novel, a character's true motive may surface only through scenes far removed from the moment it becomes relevant. This source-internal evidence integration is central to real-world long-document analysis, yet existing benchmarks largely sidestep it. Needle probes, planted facts, and reverse-engineered multi-hop chains embed evidence that may differ from the host text in distribution, placement, or register, making it unclear whether strong performance reflects genuine source reasoning or distributional artifacts. We introduce WILDTRACE, a benchmark of 481 tasks over 214 naturally occurring long-form sources such as technical incident reports and lesser-known literary narratives, where all evidence trails arise from the document's own causal, temporal, and narrative logic. Drawing on Pearl's causal hierarchy and prior multi-hop reasoning typologies, we define seven source-internal evidence geometries that characterize the distinct relational demands of analytical reading in long documents. A source-first construction pipeline mines candidate trails from document structure before writing questions; each item then undergoes multi-stage validation covering clue necessity, answer groundedness, rubric fidelity, contamination resistance and answerability. As models are increasingly entrusted with real-world high-stakes analytical tasks, this gap between accessing information and reasoning over naturally dispersed evidence emerges as a defining challenge for the next stage of long-context research.

Tingyang Chen, Shuo Lu, Kang Zhao et al.

AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts. Yet today's harnesses remain largely hand-crafted and static: each new model or task still demands bespoke scaffolding, and the rich traces produced during execution are rarely distilled back into systematic improvement. We introduce HarnessX, a foundry for composable, adaptive, and evolvable agent harnesses. HarnessX assembles typed harness primitives via a substitution algebra, adapts them through AEGIS, a trace-driven multi-agent evolution engine grounded in an operational mirror between symbolic adaptation and reinforcement learning, and closes the harness-model loop by turning trajectories into both harness updates and model training signal. Across five benchmarks (ALFWorld, GAIA, WebShop, tau^3-Bench, and SWE-bench Verified), HarnessX yields an average gain of +14.5% (up to +44.0%), with gains largest where baselines are lowest. These results suggest that agent progress need not come from model scaling alone: composing and evolving runtime interfaces from execution feedback is an actionable and complementary lever. The complete codebase will be open-sourced in a future release.

Hongyu Qu, Jianzhe Gao, Xiaobin Hu et al.

Mainstream Vision-Language-Action (VLA) models predict actions primarily from the current observation under a Markovian assumption, thus struggling with long-horizon, temporally dependent tasks. Existing memory-augmented VLAs either expand the observation window or retrieve history from the memory bank as auxiliary policy-side context. However, they leave memory outside the native latent embedding space of VLA reasoning, preventing historical experience from being fluidly interleaved with multimodal reasoning and action formation. To this end, we introduce LaMem-VLA, a latent-memory-native framework that reconstructs historical experience into latent memory tokens and directly interweaves them with VLA reasoning. At its core, LaMem-VLA introduces four coordinated components: (i) a curator that organizes historical experience into two complementary short-term and long-term memory vaults; (ii) a seeker that queries both vaults using the multimodal cognition to retrieve context-relevant evidence; (iii) a condenser that reconstructs the retrieved evidence into compact short-term and long-term latent memory tokens; and (iv) a weaver that injects these memory tokens with the current observation and instruction into one continuous embedding sequence. By representing, retrieving, and consuming historical experience entirely in the same continuous latent space, LaMem-VLA enables memory to directly participate in VLA reasoning and guide action generation under a bounded context. Extensive experiments on SimplerEnv and LIBERO demonstrate the superiority of our LaMem-VLA.

Yuanmin Xie, Xiangfan Wu, Wenhao Wu et al.

Algorithmic Complexity Vulnerabilities (ACVs) arise when adversarial inputs trigger worst-case execution behavior, causing severe performance degradation or Denial-of-Service conditions. A key but underexplored source is shadow complexity: non-trivial computational costs hidden inside seemingly benign standard library APIs. Because these costs are invisible at call sites, attackers can exploit them to induce unexpected superlinear runtime behavior. Existing ACV detectors often rely on fuzzing, symbolic execution, or hybrid analysis, but they are usually language-specific, require substantial manual effort to construct harnesses, and depend on heavy runtime instrumentation. We present ShadowProbe, a scalable and language-extensible framework for discovering ACVs through lightweight static analysis, automated reconstruction of execution contexts, and Large Language Model (LLM) assisted test generation. ShadowProbe uses a structured multi-stage pipeline: it statically screens for candidate functions guided by shadow-complexity signals, reconstructs minimal executable contexts from project-level symbols, and synthesizes size-controlled inputs to probe worst-case behavior. It then validates candidates using execution-time measurements and robust statistical growth inference, separating true algorithmic blowups from runtime noise such as garbage collection and JIT compilation effects. We evaluate ShadowProbe on the WISE benchmark, where it consistently improves analysis efficiency over existing approaches. We further apply it to large-scale systems including CPython, the JDK, Zig, Rustc, and vLLM, uncovering many previously unknown ACVs, many of which have been confirmed and partially remediated by maintainers. These results show that ShadowProbe can identify hidden algorithmic risks across diverse real-world codebases.

Wanxia Cao, Chengzhen Duan, Pei Fu et al.

Graphical user interface (GUI) agents build on vision-language models to complete user tasks end-to-end in real applications through interface actions such as tapping, swiping, text entry, and navigation. However, existing GUI agents are trained and evaluated largely on offline trajectories, simulated environments, and standardized benchmarks. These differ substantially from real applications in interface layout, interaction logic, and abnormal-state distribution, and cannot faithfully characterize execution stability in real-world use, where account states, permission dialogs, payment authentication, and risk control continually reshape the state distribution and open a persistent gap between benchmark scores and real usability. To close this gap, we propose Xiaomi-GUI-0, a native multimodal GUI agent for real mobile environments, trained and evaluated within a real-device closed loop. At its core is a real-device-dominant hybrid infrastructure, where physical devices are the primary execution environment and sandboxes provide auxiliary support, so that data collection, training, rollout, and evaluation share an execution distribution close to real deployment. We construct multi-source training data spanning high-frequency head tasks, high-generalization data for long-tail intents, and capability-enhancement data for reflection and memory, and introduce an error-driven data flywheel that turns failure trajectories into corrected actions, reflective explanations, and recovery demonstrations. The model is trained through a progressive three-stage pipeline of supervised fine-tuning, step-level reinforcement learning, and agentic reinforcement learning. Evaluated on public benchmarks and our in-house RealMobile, Xiaomi-GUI-0 achieves 72.0% success on RealMobile and 78.9% on AndroidWorld, while substantially improving execution stability and abnormal-state recognition in real-world tasks.

Yanjia Li, Kelcy Kexin Han, Tianrui Hu et al.

Simulation has long supported supply chain management instruction by letting learners observe network behavior and test decision strategies. Recent progress in LLM-driven agents opens new possibilities for richer, more adaptive simulations, but many existing systems still present abstract, opaque data that overwhelms learners and discourages active exploration. We introduce \textit{SupplyNet}, a gamified visual simulation system built on a contextual graph-based LLM multi-agent framework that models interdependent supply chain dynamics and provides responsive feedback through tiered challenges. \textit{SupplyNet} turns the simulation into a manipulable decision space by integrating an interactive network view of system state, a branching timeline for "what-if" exploration and comparison, and a task-oriented analysis console for structured performance breakdowns. Together, these visual components support counterfactual exploration, causal tracing, and comparative reasoning about outcomes. A user study suggests that \textit{SupplyNet} increases engagement and supports users' perceived understanding of supply chain dynamics, highlighting the potential of pairing contextual multi-agent simulation with visualization to advance operational comprehension.

Yanjie Zhang, Jiajun Zhu, Minyu Wu et al.

Due to educational inequality, high-quality lesson plans often mismatch the needs of disparate educational contexts. Teachers typically modify existing lesson plans to fit new contexts, but current tools instead focus on generating content from scratch, creating additional workload. Moreover, a critical gap remains in supporting teachers to quickly adapt to new learning profiles. To bridge these gaps, we present AdaPT, a system leverages LLMs to support transformation of existing lesson plans for cross-regional and differentiated instruction. AdaPT features an interactive interface that allows teachers to input student profiles, offers structured lesson representation, provides explanations for lesson-plan transformations, automatically adapts lesson content for new contexts, and supports iterative, teacher-in-the-loop refinement. We evaluated AdaPT through a user study with 9 teachers and an expert evaluation with 3 specialists. Results show that AdaPT supports workflows of teachers and offers a promising pathway toward promoting educational equity.