1
Reflected Schr\"odinger Bridge Matching
反射边界条件下Schrödinger桥匹配新方法，拓展最优传输理论在约束域的应用。
arXiv:2607.03626v1 Announce Type: new Abstract: Recent advances in generative modeling have enabled the efficient computation of Schr\"odinger bridges…
2
AgentLTL: A Trace-Verification Framework for Measuring, Enforcing, and Training Procedural Compliance in Tool-Using LLM Agents
用一阶线性时序逻辑定义过程规则，AgentLTL让LLM智能体的操作步骤可衡量、可强制、可训练，提升安全关键任务可靠性。
arXiv:2607.02599v1 Announce Type: cross Abstract: Tool-using LLM agents are usually evaluated by final-answer correctness or LLM judges. Neither captu…
3
波士顿动力 Atlas 机器人亮相世界杯，揭秘踢球技能训练过程
IT之家 7 月 7 日消息，据科技媒体 CNET 昨天报道，波士顿动力人形机器人 Atlas 于当地时间周日走上世界杯赛场，在挪威对阵巴西比赛中，将足球交给裁判。不过在正式登场之前，这台机器人已经在中场休息环节秀了一把球技。 IT之家从原报道获悉，这台机器人从球员通道走出，并在绿茵场上重现了一系列…
4
The Bidirectional Process Reward Model
提出双向过程奖励模型，突破传统单向奖励局限，提升语言模型推理与对齐性能。
arXiv:2508.01682v3 Announce Type: replace Abstract: Process Reward Models (PRMs), which assign fine-grained scores to intermediate reasoning steps wit…
5
中山大学联合团队首次实时观察到碲纳米线在液体中的生长全过程，铋籽晶调控成核与沉积效率
IT之家 6 月 20 日消息，中山大学联合北京理工大学、英国曼彻斯特大学的科研人员，利用液相透射电子显微镜，首次实时记录了半导体碲纳米结构在液体环境中的成核与生长全过程。 碲是一种窄带隙半导体材料，在电子器件、热电转换和光电器件领域具有应用前景，其性能高度依赖于纳米结构的尺寸与形貌。相关成果已于 …
6
FacProcessTwin: An LLM-Based System for Process Twin Development
用大模型赋能生产过程孪生开发，实时捕捉全局交互，效率提升新路径。
arXiv:2606.17666v1 Announce Type: cross Abstract: Process twins provide real-time representations of entire production processes. By capturing how pro…
7
小米雷军总结 YU7 八大环节测试直播：实际过程非常顺利，目前整个测试团队有 800 多人
IT之家 6 月 13 日消息，小米董事长兼 CEO 雷军今天在盐城试验场完成了一场 YU7 测试直播，随后他发布长文，对本次直播进行了总结。 雷军表示，今天的测试共有 8 大环节、26 个项目、11 项挑战， 原计划 7 个小时，实际测试过程非常顺利，只用了 5 个半小时就全部完成 。测试车型是 …
8
PaLMR: Towards Faithful Visual Reasoning via Multimodal Process Alignment
PaLMR通过多模态过程对齐实现可信视觉推理，提升大模型对图像的理解与逻辑一致性。
arXiv:2603.06652v2 Announce Type: replace-cross Abstract: Reinforcement learning has recently improved the reasoning ability of Large Language Models …
9
Bellman-Taylor Score Decoding for Markov Decision Processes with State-Dependent Feasible Action Sets
提出贝尔曼-泰勒分数解码方法，解决状态依赖可行动作集下MDP的优化难题，为强化学习提供新视角。
arXiv:2606.10979v1 Announce Type: new Abstract: Many Markov decision processes (MDPs) in operations research have feasible actions that are state depe…
10
Memory Beyond Recall: A Dual-Process Cognitive Memory System for Self-Evolving LLM Agents
突破传统记忆局限：双过程认知记忆系统让LLM智能体实现自进化学习。
arXiv:2606.09483v1 Announce Type: new Abstract: Long-term memory for an LLM agent is more than retrieving the right passage at the right time. Current…
11
12
Can Large Language Models Generalize Procedures Across Representations?
揭秘LLM能否在不同任务表示间泛化过程，ICML 2026收录的前沿研究
arXiv:2602.03542v2 Announce Type: replace Abstract: Large language models (LLMs) are trained and tested extensively on symbolic representations such a…
13
Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes
用高斯过程提升大型视觉语言模型的语义不确定性量化能力，带来更可靠的评估方法。
arXiv:2512.14177v3 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) often produce plausible but unreliable outputs, making robust…
14
From Prompt to Process: a Process Taxonomy and Comparative Assessment of Frameworks Supporting AI Software Development Agents
提出过程分类法，系统评估支持AI软件开发代理的各类框架，从提示驱动迈向流程驱动。
arXiv:2606.04967v1 Announce Type: cross Abstract: AI tools for programming are no longer just autocomplete or chat assistants: they organize themselve…
15
Show HN: Realistic procedural fire effect via naive algorithm
仅用朴素算法实现的逼真火焰特效演示，视觉效果惊艳且代码开源可学习。
Source code: https://github.com/Leftium/fx/blob/main/src/routes/fire-plas... I made this naive fire effect as realistic as possible; arguably more rea…
16
StepPRM-RTL: Stepwise Process-Reward Guided LLM Fine-Tuning for Enhanced RTL Synthesis
逐步过程奖励引导LLM微调，提升RTL合成质量的创新方法
arXiv:2606.04246v1 Announce Type: new Abstract: Automatic generation of RTL code for digital hardware designs remains challenging due to long-horizon …
17
ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents
提出ARBOR框架，用可复用评分缓冲为搜索代理提供在线过程奖励，显著提升推理与搜索效率。
arXiv:2606.03239v1 Announce Type: new Abstract: LLM-based search agents are trained predominantly with outcome-only reward, leaving the search process…
18
AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents
最新基准AgentProcessBench，精准诊断工具使用Agent每一步的过程质量，从结果到过程全面评估Agent可靠性
arXiv:2603.14465v2 Announce Type: replace Abstract: While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in lon…
19
Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning
无需额外训练，用现成大模型就能给数学推理过程打分，性能媲美专用过程奖励模型。
arXiv:2606.01682v1 Announce Type: cross Abstract: Selecting the best response from multiple small-model samples using a stronger scorer is a simple in…
20
Why I Built the First Procedural MVC PHP Framework in 2026
首个过程式MVC PHP框架，在2026年用过程式风格重构MVC开发，兼顾简洁与架构
Why I Built the First Procedural MVC PHP Framework in 2026 NoClass is a modern MVC (Model-View-Controller) PHP framework built around procedural appli…