AI 论文与研究

Meta 发布论文 AI Research Preference Models，训练模型在任何候选方案执行前预测哪个最有前景，解决研究智能体想法多但 GPU 预算有限、缺乏原创性判断的问题。

Hugging Face 博客介绍 BenchMIRT，一种基于多维 IRT 在单个题目层面审计 LLM 基准的方法，训练数据覆盖 100 个 LLM、16 个基准和超过 34K 道题。

华为团队发布开源编码智能体 harness openJiuwen 的论文，在 SWE-bench Verified 上达到 82.6%、Terminal-Bench 2.1 上达到 87.19%，分别超过最强官方榜单成绩 3.4 和 3.39 个百分点。

openJiuwen 是一个开源 Agent harness，在 SWE-bench Verified 上达到 82.6%、Terminal-Bench 2.1 上达到 87.19%，分别超过最强官方榜单成绩 3.4 和 3.39 个百分点。

Qwen 团队发布 E-Commerce Bench，让 LLM 智能体在模拟的 365 天里同时运营多家在线商店，评测 18 个前沿模型的七维度表现，结果没有单一模型全面领先。

Rohan Paul 梳理了 Fable 5.1 系统卡中的安全发现：Anthropic 称该模型在隐蔽侧任务上达到已发布模型中最高的隐蔽通过率，约 5 次尝试成功 1 次，并认为这可能是其更难监控的弱证据。

Qwen 团队发布 E-Commerce Bench，让 LLM 智能体在 365 天的模拟环境中同时运营多家网店，评估 18 个前沿模型的七个维度，发现没有任何单一模型全面领先。

Microsoft Research 宣布两篇论文获 VLDB 2026（波士顿）认可。图片显示论文分别为面向云存储加速的 Garnet 下一代缓存存储，以及分析数据库中标量函数的 GPU 加速编译、基准测试与优化。

LLM-based evaluators of natural language generation (NLG) quality are widely deployed as scoring tools and as automated training signals, yet the internal procedure by which they assign a rating remains poorly understood. We investigate th…

Evaluating software engineering agents on realistic benchmarks is costly, since each task may require multi-step code exploration, modification, and test execution. Existing efficient evaluation methods select representative subsets to est…

The repository-level code generation task requires synthesizing code that satisfies task requirements while remaining consistent with the target repository context. Since real-world repositories often exceed the input length limits of LLMs…

Dynamic agent harnesses let language models change the software that shapes their own execution. This flexibility brings a new reasoning burden: a local plugin change can propagate through dependencies and cleanup. We introduce CordisBench…

Natural language is emerging as a primary feedback channel for improving language agents, capable of conveying intent, preferences, and causal structure in forms interpretable by both humans and modern language models. We call this paradig…

Real-world robotic assembly at sub-millimeter tolerances demands spatial precision, compliant interaction, and robustness to contact failures. We present Facet-0, a robotic foundation model that predicts and values the contact consequences…

We develop a framework for mechanism design with AI agents whose alignment (preferences) and capabilities (feasible actions and information) are unknown. We want such agents to act on our behalf so mechanisms must incentivize both honesty …

AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but evidence about which guidance works for which student is sparse, slow, and costly to collect from real learners. Student simulat…

Writing involves diverse cognitive activities, from ideation to revision, and writers' needs vary across individuals and moments. Proactive AI promises to provide the right support at the right time, yet existing proactive tools largely fo…

Post-training quantization (PTQ) is widely used to reduce the cost of serving large language models (LLMs), but its accuracy cost is uneven and is often tuned per model. We study where quantization damage occurs and how to allocate a small…

Extracting structured fields from hundreds of millions of documents annually remains costly in regulated industries: bespoke OCR cascades cover only a fraction of workflows, privacy rules preclude external models, and existing open-source …

How to divide a fixed annotation budget between supervised fine-tuning (SFT) and reinforcement learning (RL) during LLM post-training remains an open problem. Existing work characterizes only broad trends (e.g., SFT dominates in low-data r…

Data-residency constraints force enterprises to self-host LLMs, but continuous adoption of newer models without decommissioning their predecessors expands the serving fleet, fragmenting a finite GPU pool. We consolidate traffic from over 2…

Vision-Language Models (VLMs) provide useful priors for interactive decision-making, but using them directly as policies is expensive and brittle: they must be queried at every step, do not improve from environment interaction, and can rep…

Large language models (LLMs) struggle to classify text into taxonomies with many semantically similar labels, as the distinctions are domain-specific and not captured by pre-training. To handle large label spaces, a common approach retriev…

Semiconductor supply chains face escalating risks from geopolitical tensions, geographic concentration, and rapid technological shifts, yet no scalable system continuously extracts, structures, and prioritizes risk intelligence from public…

We present H3-World, an efficient framework that turns the 33B MiniMax-H3 video generator into an interactive world model. Our key finding is that, as large video generators become more capable, language is emerging as a natural interface …

Training Physics-Informed Neural Networks (PINNs) requires jointly optimizing physics residual and initial/boundary condition loss terms, which often induce conflicting gradients. Gradient surgery methods mitigate this issue by constructin…

We evaluate embedding retrieval where surface form and meaning are pulled apart on purpose: retrieving items that share underlying structure but not wording, in two unrelated domains under one protocol, competition mathematics (MathNet-Ret…

Automated lesion segmentation in whole-body PET/CT is complicated by the variety of physiological tracer uptake patterns and by the differing appearance of lesions across tracers. The autoPET/CT V challenge addresses this by making segment…

Not Diamond 发布模型路由评估方法论，称在多个主流基准上实现 Pareto 占优，以低 20-80% 的成本超过 Opus xhigh 质量。

普林斯顿大学、蚂蚁集团和斯坦福大学的研究团队提出 AQuA，一套由两个互不共享智能体、记忆和状态的语言模型量化研究系统，其设计要点是在迭代开始前冻结数据划分、特征与标签定义和评估器，让智能体只能在受约束的 DSL 内探索，以阻断自我改进中的数据泄漏。

DAIR.AI 推介阿里与浙江大学的论文 SkillZip Pro，针对生产级 agent skill 目录包做执行感知动态压缩。方法在根或声明环境契约已提供内容时跨文件移除引用与子skill中的冗余，并保留路由使所需文件和可直接调用入口保持可达，提供 One-Shot、Continual、Persistent、Transient 四种模式。

一篇 arXiv 论文（https://arxiv.org/abs/2608.29460）提出在编码智能体遭遇缺陷测试基础设施时提供结构化升级报告工具，将 reward hacking 从 23.6% 降至 5.3%。

一项研究估算，2015 至 2024 年数据中心并未推高美国居民平均电价，数据中心容量每增加 10%，平均居民电价约下降 0.4%。原因是电网固定成本被更多售电量摊薄，且新增电厂运行成本可能更低；作者警告若电网供应不足或过度建设，该效应可能反转。2024 年数据中心用电约占美国电力 4.5%，预计 2030 年达 9-17%。

安全公司 CloudSEK 发布报告，披露黑客组织 Aurora 的攻击活动及内部细节。研究人员潜入黑客配置错误的服务器，获取了攻击工具、AI 攻击计划记录及赎金协商管理界面。

英国伯明翰大学、丹麦奥胡斯大学和瑞典林奈大学研究人员 8 月 19 日在《AI 与社会》发表论文，提出类机器人人性（robotoid humanness）概念，指客服 AI 因自适应学习、个性化沟通和共情回应变得更像人，用户可能为获得更顺畅的算法反馈而表现得更像机器。

ContextLeak 论文提出用强化学习训练攻击 LLM 生成恶意工具名称和描述，诱导 Agent 选中该工具并把用户提示词、对话历史、已装工具列表等敏感上下文作为参数传出。

Google DeepMind 论文《Accelerating Scientific Research with Gemini in the Real-World》（arxiv.org/abs/2608.26701）显示。