SWE Refactor Bench：编码智能体全仓重构存活率仅5.4%

DeepMind的AI co-mathematician在FrontierMath Tier 4研究级数学问题得分48%，而基础模型Gemini 3.1 Pro仅19%。提升源于多代理架构的智能编排，包括并行代理相互审查证明、编写代码和搜索文献，而非模型本身更智能。评估绕过标准框架，使用48小时每问题、无令牌限制的自有基础设施，因此得分不能直接与其他模型比较。案例中，数学家Marc Lackenby与AI合作解决Kourovka Notebook开放问题，AI提供证明策略，…

在无中央协调器的开放世界多智能体环境Station中，来自不同模型家族的AI智能体自主选择研究方向、开展实验并构建共享科学文献。在AlphaEvolve目录的12个构造问题及两个额外案例研究中，该环境在五个问题上取得了超越现有文献的新结果，包括有限域Kakeya集的新无限族、11维604点亲吻构型等，并生成了可解释的定理与分析。所有原始智能体对话、证明和验证代码均已公开。

斯坦福大学研究人员领衔发布 Terminal-Bench-Science 0.1，用来自生命、物理、地球、数学和工程科学的 70 个专家精选任务评估 AI 智能体的科研能力。

Recent advances in inference-time scaling have significantly improved the reasoning performance of large language models (LLMs). However, these methods typically rely on repeated generation or external verification. To address this limitat…

Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which enables agents to progressively adapt through …

Recent prominent post-training methods, such as Reinforcement Learning (RL) and On-Policy Self-Distillation (OPSD), have driven rapid progress in mathematical reasoning for large language models, yet their reliance on ground-truth labels p…

To improve large language models' ability to resolve real-world software issues, prior work has focused on constructing large-scale agent trajectory datasets and performing supervised fine-tuning (SFT) on successful trajectories. However, …

In real-world software development, code review typically involves iterative interactions between developers and reviewers to improve software quality, making the process costly and time-consuming. Although recent work explores large langu…

LLM-based agents are increasingly deployed in product-level execution harnesses, where jailbreaks can trigger harmful tool use and persistent state changes, creating greater risks than unsafe text generation alone. Existing automatic red-t…

Chemical reactions are fundamentally transformations in electron space, yet most machine learning approaches model them either through \textit{de novo} generation of product molecules or through heuristic graph edits that operate directly …