👍 202
09/28 08:00
Latent visual reasoning (LVR) enables multimodal large language models (MLLMs) to perform intermediate computation in continuous latent tokens rather than expressing every reasoning step in words. However, unlike textual CoT, latent reasoning is not directly observable, making it difficult to superv
中文介绍 针对潜空间视觉推理(LVR)中间步骤不可观测、难以监督的问题,论文提出将潜在推理锚定到视觉证据上的方法,使 MLLM 在连续 latent token 中计算时仍与图像区域对应,从而提升可解释性与推理可靠性。
👍 188
09/30 08:00
Self-evolving search agents build their own training curricula by jointly optimizing a proposer that generates questions and a solver that answers them. This closed loop introduces a failure mode we call co-cheating: the proposer and solver increasingly agree on shared errors, so internal reward imp
中文介绍 自演化搜索智能体由出题者与解题者共同优化,形成闭环后会互相认同共同错误,论文将这一失效模式命名为 co-cheating,并给出诊断方法及缓解策略,以抑制内部奖励被共享偏差劫持。
👍 98
09/30 08:00
Terminal agents act through stochastic model generations, yet the ability to generate a useful action does not ensure its reliable execution. A poor command (e.g., wrong package install) can change the environment in ways that hinder subsequent progress, even when the model could generate a better a
中文介绍 终端智能体的动作生成与可靠执行之间存在落差,错误命令会污染环境状态。Mid-Harness 在模型与执行外壳之间引入中间层来缩放动作,从而提升命令执行的可靠性与后续任务进度。
👍 63
09/29 08:00
Large language models (LLMs) are increasingly deployed as agents for multi-step decision-making, yet transfer poorly to unseen environments. World-model methods address this by training agents to predict future observations, at the cost of additional training and errors that compound when prediction
中文介绍 针对 LLM 智能体跨环境迁移差的问题,EVOKE 不额外训练世界模型,而是从模型中激发已有世界知识用于多步决策,减少预测误差累积,提升在未见环境下的可迁移决策能力。
👍 30
09/29 08:00
Recent advances in musculoskeletal modeling and reinforcement learning have enabled muscle-actuated agents to reproduce increasingly complex human motions. Yet these capabilities remain largely confined to flat ground, in part because motion datasets rarely include aligned terrain geometry and becau
中文介绍 肌肉骨骼运动控制研究多局限于平地,缺乏对齐地形几何的数据。TERRA 提出地形感知的重建、重定向与控制流程,使肌肉驱动智能体能在复杂地形上复现人体运动。
👍 24
09/29 08:00
We introduce LoopVL to study whether Loop Transformers can be effectively extended to vision- language models. LoopVL combines Module-Loop and Model-Loop computation to iteratively update a unified vision-language state through shared modules. We train LoopVL from scratch through language pre-traini
中文介绍 LoopVL 探索将 Loop Transformer 扩展到视觉语言模型,结合 Module-Loop 与 Model-Loop,通过共享模块迭代更新统一视觉语言状态,并从头经语言预训练等阶段训练,验证循环计算在视觉语言任务上的可行性。
👍 24
09/30 08:00
Scientific software presents a demanding test for computer-using agents based on visual language models (VLMs): completing a research workflow requires interpreting specialized interfaces, manipulating scientific objects, and producing verifiable results. We thus introduce OSWorld-Science, a benchma
中文介绍 论文提出 OSWorld-Science 基准,用于评测基于 VLM 的计算机使用智能体操作科学软件的能力,任务涵盖解析专业界面、操作科学对象并产出可验证结果,填补科研工作流端到端评测的空白。
👍 18
09/26 08:00
Reward models score responses from large language models (LLMs) and guide LLM training toward human preferences. However, reward models can favor superficial attributes such as length or confidence, leading LLMs to produce higher-scoring but not more correct responses. Existing mitigation methods ei
中文介绍 奖励模型常偏好长度、自信度等表层属性,导致 LLM 输出得分高但未必正确。BiasReducer 提出自适应偏差缓解方法,在不牺牲奖励信号有效性的前提下削弱此类捷径偏差,引导训练更贴近人类偏好。
👍 16
09/30 08:00
Looped transformers and Mixture-of-Experts (MoE) offer complementary routes to efficient scaling: recurrence increases computational depth at fixed parameters, while MoE sparsity expands total capacity at fixed active compute. Yet existing scaling laws model recurrence or sparsity in isolation. In t
中文介绍 循环 Transformer 与 MoE 分别从深度和容量两条路径实现高效扩展,但现有 scaling law 只单独建模其一。该工作提出统一缩放律,联合刻画循环次数与专家稀疏度对损失的影响,指导二者的协同配置。
👍 15
09/29 08:00
Modern agentic systems combine an AI model with a harness that controls execution and environmental interactions. Harness design strongly affects long-horizon performance, yet its combinatorial search space demands substantial human effort that must be repeated as models change. Existing automated m
中文介绍 智能体外壳设计对长程表现影响大,但组合搜索空间依赖大量人工试错。MILO 通过多智能体协同演化自动发现外壳,随模型更替可重复搜索,降低人工成本并提升长程任务性能。
👍 13
09/26 08:00
Software development requires more than editing code: developers repeatedly run software, interact with its interfaces, visually inspect its behavior, and use these observations to decide what to change next and whether a change works. Existing coding agents and computer-use agents are largely studi
中文介绍 软件开发不仅需要改代码,还需运行软件、观察界面行为并据此决策。CUA-SWE 研究将计算机使用智能体与视觉软件工程结合,让智能体通过界面观察驱动代码修改与验证,拓展现有编码智能体的能力边界。
👍 8
09/29 08:00
TTS systems with autoregressive semantic modeling have demonstrated strong zero-shot voice cloning performance and rich expressive variation, but their sequential decoding incurs substantial latency. Non-autoregressive alternatives offer much faster generation, yet often rely on more restrictive ref
中文介绍 自回归语义建模的 TTS 零样本音色克隆效果好但解码延迟高。Tacit-TTS 改用以掩码预测为核心的非自回归框架,在无需转录文本的条件下实现高效语音克隆,兼顾生成速度与音色还原。
👍 6
09/30 08:00
Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and latency overhead of text-based communication. To this end, lightweight trainable links are introduced to map the sender's representations into the
中文介绍 多智能体系统通过内部表示空间的潜通信可降低 token、计算与延迟开销,但绕过文本后安全风险未知。该工作系统分析潜通信链路引入的安全问题,并探讨相应的防护与评估方向。
👍 6
09/30 08:00
Self-attention gives LLMs fine-grained, query-dependent access to context, but dense token interactions incur quadratic prefill cost and a key--value cache growing with context length. Research thus spans explicit-memory compression, sparse access, recurrent state construction, structured state dyna
中文介绍 该综述梳理 LLM 注意力机制的演进:自注意力带来细粒度上下文访问,但 prefill 呈二次开销、KV cache 随长度增长。文章按显式记忆压缩、稀疏访问、循环状态构建与结构化状态动力学等路线归纳机制、权衡与新兴趋势。
👍 5
09/30 08:00
We study training LLM judges from natural language feedback, especially for subjective tasks where the verdict depends strongly on which evaluation criteria the judge invokes and how it weighs them. The dominant approach, outcome-supervised RL (e.g., GRPO), credits every token in the rollout with a
中文介绍 针对主观任务中评判标准选择与权重影响判决的问题,论文提出从自然语言反馈训练 LLM 评判器,用位置选择性自蒸馏替代 GRPO 式结果监督 RL,将信用分配到关键位置,提升评判质量。
👍 5
09/28 08:00
Large language model (LLM) routing aims to select the most suitable model for each incoming query. Most existing routers learn this decision directly from query embeddings, model representations, preference data, or clusters of similar examples. Such approaches can be effective, yet the representati
中文介绍 现有 LLM 路由多直接从查询嵌入、模型表示或偏好数据学习决策,表示语义有限。SeLMRoute 引入概率化语义证据进行路由,为每个查询选择更合适的模型,提升路由的准确性与可解释性。
👍 4
09/28 08:00
Artificial-intelligence (AI) agents hold promise for automating bioimage analysis, yet no benchmark evaluates whether they can carry out real-world analyses end to end. Such analyses are hard for agents because 2D images, 3D volumes and time-lapse sequences are often too large to read as context, so
中文介绍 论文提出 BIABench,评测 AI 智能体能否端到端完成真实生物图像分析任务,涵盖 2D 图像、3D 体数据与延时序列等超出上下文长度的场景,为生物图像自动化分析提供系统化基准。
👍 4
09/30 08:00
We find that major reported improvements in decoding words from non-invasive brain recordings are largely reproducible without any brain data. In the influential work of d'Ascoli et al. (2025), time series of brain activity from subjects perceiving continuous speech are segmented into fixed-length w
中文介绍 论文发现非侵入式脑电到文本解码中的显著提升可脱离脑数据复现,源于固定长度分段带来的时间捷径。移除该类捷径后重新评估,揭示既往结果被高估,并为该任务提供更严格的评测设定。
👍 4
09/29 08:00
Skills equip LLM agents with professional knowledge and guidance to complete long-horizon and complex tasks. Although skills have been widely adopted in recent agent paradigms and harnesses, how to synthesize reliable training data and how to train agents for skill use remain underexplored. In this
中文介绍 技能可赋予 LLM 智能体专业知识,但训练数据合成与技能使用训练仍缺乏研究。SkillGym 通过自动生成可验证环境来训练技能使用智能体,为长程复杂任务提供可扩展的训练数据与训练流程。
👍 4
09/30 08:00
Persistent spatial memory enables embodied agents to navigate familiar environments across repeated visits. However, targets may move while unobserved, including during navigation, making remembered locations unreliable by the time an agent arrives. Despite advances in memory retrieval and state pre
中文介绍 持久导航中目标可能在未被观察时移动,仅靠记忆位置并不可靠。论文提出预测式 4D 信念表示,在记忆之外推断目标随时间演化的状态,从而在动态环境中实现更稳健的持续导航。