👍 85
06/23 08:00
A world model predicts environment dynamics based on current observations and actions, serving as a core cognitive mechanism for reasoning and planning. In this work, we investigate how world modeling based on language models can further push the boundaries of general agents. (i) We first focus on b
中文介绍 提出Qwen-AgentWorld,利用语言模型构建世界模型预测环境动态,增强通用智能体推理与规划能力。探索语言世界建模对智能体性能的推动作用。
👍 47
06/23 08:00
We introduce NatureBench, a cross-discipline benchmark of 90 tasks distilled from peer-reviewed Nature-family publications, designed to evaluate whether AI coding agents can move beyond reproduction toward discovery on real scientific problems. NatureBench is built on NatureGym, an automated pipelin
中文介绍 提出NatureBench,从Nature系列论文中提取90个跨学科任务,评估编码智能体在真实科学问题上的发现能力。基于NatureGym自动流水线,衡量是否达到已发表SOTA。
👍 34
06/18 08:00
MLLM-based mobile GUI agents have made substantial progress in UI understanding and action execution, but adapting them to real target apps remains costly because mobile apps are numerous, frequently updated, and hard to cover with human-written tasks, demonstrations, or reward labels. Existing anno
中文介绍 提出MobileForge,无需人工标注即可适配移动GUI智能体到真实应用。采用层次化反馈引导策略优化(HFPO),解决应用频繁更新带来的标注成本问题。
👍 33
06/18 08:00
MLLM-based mobile GUI agents have made substantial progress on short-horizon tasks, yet remain unreliable on long-horizon tasks that require retaining intermediate facts across many steps and app transitions. We attribute this limitation to ReAct-style prompting, which passively accumulates per-step
中文介绍 提出MemGUI-Agent,解决MLLM移动GUI智能体在长时序任务中不可靠的问题。采用主动上下文管理替代ReAct式被动累积,实现跨多步和应用切换的中间事实保持。
👍 25
06/22 08:00
AI agents are driving a new software paradigm, with the ability to autonomously call tools, extract information, manage memory, and complete tasks that span applications and data sources. Most existing end-user operating systems, however, are designed for application-centric workflows and offer litt
中文介绍 提出AOHP,开源操作系统级智能体框架,支持自主调用工具、提取信息、管理记忆,完成跨应用任务。为个性化、高效和安全交互设计。
👍 25
06/23 08:00
Agentic language models dramatically expand the applications of AI yet little is publicly known about how to curate training data for broadly capable agents. Existing open efforts such as SWE-Smith, SERA, and Nemotron-Terminal typically target a single benchmark, leaving open the question of how to
中文介绍 提出OpenThoughts-Agent,研究通用智能体模型的数据配方。现有开源工作仅针对单基准,该工作探索多任务数据,旨在提升智能体广泛能力。
👍 20
06/20 08:00
We present BioMatrix, the first multimodal foundation model that natively integrates sequences, structures, and natural language for both molecules and proteins within a single decoder-only architecture. Existing biological foundation models pursue native multimodality and broad entity coverage sepa
中文介绍 提出BioMatrix,首个原生集成序列、结构和自然语言的多模态基础模型,采用单一解码器架构同时覆盖分子和蛋白质,实现多模态融合与广泛实体覆盖。
👍 19
06/11 08:00
Mental disorders are highly prevalent worldwide, but the shortage of psychiatrists and the inherent subjectivity of interview-based diagnosis create substantial barriers to timely and consistent mental-health assessment. Progress in AI-assisted psychiatric diagnosis is constrained by the absence of
中文介绍 提出LingxiDiagBench,多智能体框架,用于评估LLM在中文精神科咨询和诊断中的表现。解决精神科医生短缺和诊断主观性,提供标准化测试。
👍 13
06/22 08:00
Modern text-to-image models excel in visual fidelity and prompt adherence. However, this strict adherence comes at the cost of diversity: generated samples tend to collapse into a single visual interpretation. Existing methods to improve diversity produce outputs driven by incidental variations rath
中文介绍 提出Semantic Browsing,一种可控多样性的图像生成方法。现有文本到图像模型多样性不足,该方法通过语义浏览生成可控变化的输出,而非偶然变异。
👍 13
06/23 08:00
Generating explorable 3D scenes from a single image requires strong generative priors and accurate geometric representations suitable for downstream use. Current video diffusion models offer high-quality generation and implicitly encode multi-view geometric structure in latent space. However, existi
中文介绍 提出FLAT,从单张图像生成几何精确的可探索3D场景。利用前馈潜在三角形泼溅,结合视频扩散模型多视角先验,实现高质量生成与准确几何表示。
👍 10
06/10 08:00
Scientific discovery workflows usually contain and rely heavily on lab notes, where researchers record observations, interpret uncertain results, and plan follow-up experiments. Such informative lab notes preserve evolving scientific reasoning and author uncertainty, rather than polished final resul
中文介绍 提出Notes2Skills,将实验室笔记转化为具有不确定性感知的科学智能体技能。利用笔记中记录的不确定结果和推理,构建可复用的代理技能。
👍 8
06/23 08:00
Experience-driven self-evolution is critical for large language model (LLM) agents to improve through open-world interaction. However, existing experience learning methods mostly rely on single-agent loops, where the same agent executes tasks, summarizes outcomes, and determines memory content. This
中文介绍 提出执行-蒸馏-验证(EDV)范式,打破单智能体循环中自我确认的陷阱。通过多角色协作,避免同一智能体既执行又总结带来的偏差。
👍 7
06/22 08:00
What is an agent? What constitutes agency? With the rise of Large Language Model (LLM) systems marketed as ``coding agents'', ``AI co-scientists'', and other ``agentic" tools that promise to drive up productivity, and at the same time, ``existential" concerns such as AI escaping human control with d
中文介绍 批判性分析当前LLM代理系统的定义、自主性和风险。探讨“编码代理”、“AI共同科学家”等概念及AI失控等存在性担忧。
👍 7
06/19 08:00
Open-weight Large Language Models (LLMs) enable scientific progress and broad deployment. However, they make it difficult to control access to sensitive capabilities. Current practice either suppresses dangerous capabilities before release or mediates access through closed services that use speciali
中文介绍 提出开放权重模型的风险控制方法,通过分离公开和私有能力,在推动开放科学的同时控制敏感能力使用,避免发布后滥用。
👍 6
06/22 08:00
Video diffusion models have enabled remarkable progress in video generation and editing. However, content preservation remains a core challenge: existing methods regenerate every pixel and often alter elements that should remain unchanged, such as characters or background scenes. We introduce Vera,
中文介绍 提出Vera,一种分层扩散模型,在视频编辑中保持内容不变(如角色、背景)。现有方法重绘每像素,Vera通过逐层编辑保留原元素。
👍 6
06/19 08:00
As agentic systems tackle increasingly complex multi-step tasks, evaluating their trajectories presents a major bottleneck - human annotation of a single trajectory on popular agentic benchmarks can take hours, making it difficult to scale evaluations for measuring performance or curating training d
中文介绍 提出Counsel,用于智能体轨迹评估的元评估数据集。解决人工标注耗时问题,支持可扩展的性能评估和训练数据筛选。
👍 5
06/23 08:00
Text-to-image (T2I) generation models have achieved remarkable progress in producing visually realistic images from natural language prompts. Yet it remains unclear whether their success reflects genuine causal understanding or sophisticated pattern matching over visual-textual correlations. Inspire
中文介绍 提出反事实基准,测试文本到图像模型是否具有真正的因果理解,还是仅依赖模式匹配。通过反事实案例评估模型因果推理能力。
👍 4
06/17 08:00
Long-context reasoning is an essential capability for large language models, particularly when they are deployed as autonomous agents that must reason over lengthy trajectories. Reinforcement learning (RL) has recently emerged as a dominant paradigm for improving this ability, yet existing work larg
中文介绍 提出长上下文强化学习的数据配方,超越奖励工程。针对智能体长轨迹推理,通过数据构建而非复杂奖励设计来提升RL效果。
👍 4
06/22 08:00
Reconstructing dynamic non-rigid objects from monocular video requires integrating visual cues from direct observations with data-driven priors over geometry and appearance. Prior approaches either learn to directly predict 4D representations from visual input or initialize a 3D representation that
中文介绍 提出Lift4D,从单目视频中重建动态非刚体4D场景。融合视觉观测与数据先验,和谐整合单视图3D估计,实现野外4D重建。
👍 3
06/22 08:00
Scaling reinforcement learning for visual mathematical reasoning requires more than generating harder questions: as data volume grows, the reward labels themselves must remain reliable. Yet existing data pipelines scale supervision while trusting the labeller, and policy-side methods assume the unde
中文介绍 提出VeriEvol,通过可验证的Evol-Instruct扩展多模态数学推理的强化学习。保证大规模数据中奖励标签的可靠性,解决现有监督扩展的可信问题。