CRUX 项目提出"开放世界评估"测试前沿AI能力

普林斯顿大学研究人员将AI智能体可靠性分解为4个维度共12项指标，对14个模型测试发现，近18个月能力快速进步仅带来有限的可靠性提升，一致性得分仅30%-75%。研究团队计划推出"可靠性指数"以推动系统性改进。

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 …