基于信息增益的展开策略优化论文亮相arXiv

近日，一篇题为“Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents”的论文被提交至arXiv预印本平台。该论文由Yijun Zhang等9位作者共同完成，提出了一种基于信息增益的展开策略优化（IG-RPO）方法。该方法采用自适应树结构展开，旨在优化多轮大语言模型（LLM）代理的决策策略。当前论文在计算机科学（cs）领域下浏览，并已获得arXiv编号，其DOI正在注册中。这项研究或为多轮对话AI的策略学习提供新的思路。 #arXiv #论文 #LLM

Anthropic 回顾 Claude Code 诞生历程

Anthropic 近日发布 Claude Code 的诞生故事，回顾其从内部命令行工具 clide 成长为重要 AI 代理产品的过程。早期，团队致力于让模型学会写代码和生成 diff，并开发出笨拙但极具前瞻性的 clide 工具，首次展示了 AI 自主编程的潜力。2024 年，Ben Mann 组建 Labs 团队，Boris 快速制作出 demo，促使 Claude Code 正式立项。2025 年，Claude Code 亮相并开放使用，逐步融入开发流程，最终成为 Anthropic 证明 AI 可进入真实工作现场的核心样板。这一历程揭示了产品从内部工具到行业标杆的进化路径。 #ClaudeCode #Anthropic #AI编程 #AI代理 #大模型 #科技新闻 #开发工具 #代码生成

论文提出人类

据arXiv预印本，一篇题为《A toy framework for single and multi-agent human-AI curiosity ecosystems》的论文正式提交。该研究由Ilya E. Monosov完成，于2026年7月7日发布。论文提出了一个简化模型（玩具框架），用于模拟单智能体和多智能体环境中人类与AI之间由好奇心驱动的交互机制。好奇心被视为探索与学习的核心驱动力，该框架通过构建抽象交互规则，分析了不同智能体如何基于好奇心进行信息寻求，以及这种机制在集体探索中的协作或竞争效应。研究为理解人机协同中的自主探索行为提供了理论基础，可能对未来AI系统在开放环境下的主动学习、自我引导探索及人机协作设计具有启发性。 #AI #好奇心 #多智能体 #单智能体 #框架 #arXiv #预印本 #人机协作 #论文

Telegram必备的搜索引擎，极搜JISOU帮你精准找到，想要的群组、频道、视频、音乐

👉 t.me/jisou2?start=a_8247614025

When do prophets profit in prediction markets?

Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Haifeng Xu [ view email ] [v1] Tue, 7 Jul 2026 11:41:46 UTC (311 KB) Full-text links: Access Paper: View a PDF of the paper titled When do prophets profit in prediction markets?, by Anri Gu and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: < prev | next > new | recent | 2026-07 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litma

ps ( What is Litmaps? ) Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle ( What is ? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

奖励密度启发式算法提升动态多车辆路径规划性能

近日，一篇题为《Reward-Density Heuristic for Dynamic Multi-Vehicle Routing: Performance and Computational Efficiency》的论文在arXiv预印本平台上线。该论文由Manish Kolachalam和Rani Malhotra共同撰写，针对动态多车辆路径问题提出了一种基于奖励密度的启发式算法，并系统评估了其性能与计算效率。动态多车辆路径问题在物流配送、紧急响应等场景中具有重要应用，该研究为实时路径优化提供了新的算法思路。论文目前处于等待DOI注册阶段，全文可通过arXiv网站获取。 #动态多车辆路径 #启发式算法 #奖励密度 #性能评估 #计算效率 #arXiv #预印本 #物流优化 #算法研究

PolyWorkBench：多语言长周期LLM代理性能评估基准发布

来自香港理工大学等机构的研究团队在arXiv上提交了一篇论文，提出了一个新的基准测试PolyWorkBench，专门用于评估大型语言模型在多语言、长周期任务中的代理能力。该基准模拟了需要长期规划和持续交互的复杂场景，涵盖多种语言环境，旨在填补现有LLM评估中缺乏多语言长周期任务标准的空白。PolyWorkBench通过一系列精心设计的任务，测试模型在理解、记忆、推理和多步执行等方面的综合表现，为研究多语言AI代理的可靠性和实用性提供了重要参考工具。该基准的发布有望推动LLM在全球化、多语言实际应用中的发展。 #PolyWorkBench #LLM #多语言 #AI代理 #基准测试 #学术研究 #arXiv

Information Limits and Attractor Dynamics in Economies of Frontier LLM Agents: A Pre

Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Cheng Qian [ view email ] [v1] Tue, 7 Jul 2026 08:39:24 UTC (35 KB) Full-text links: Access Paper: View a PDF of the paper titled Information Limits and Attractor Dynamics in Economies of Frontier LLM Agents: A Pre-Registered Test, by Cheng Qian View PDF HTML (experimental) TeX Source view license Current browse context: < prev | next > new | recent | 2026-07 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers

Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle ( What is ? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

AgoraSim：一种混合代理基建模框架在arXiv发布

近日，一篇题为"AgoraSim: A Hybrid Agent-Based Modeling Framework"的论文在arXiv预印本平台正式发布。论文由Chung-Chi Chen撰写，于2026年7月7日提交。该研究提出了一种名为AgoraSim的混合代理基建模框架，为复杂系统模拟提供了新的思路。论文目前提供PDF、HTML及TeX源码等多种格式，其DOI正在通过DataCite注册中。该论文归属于计算机科学领域，感兴趣的读者可通过arXiv免费获取全文。 #arXiv #代理基建模 #混合模型 #学术论文 #计算机科学 #AgoraSim #2026

Auto-DSM Under the Lens: A Black-Box Evaluation Framework for LLM-Based DSM Generation

Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Theo Hofman [ view email ] [v1] Tue, 7 Jul 2026 08:17:49 UTC (1,631 KB) Full-text links: Access Paper: View a PDF of the paper titled Auto-DSM Under the Lens: A Black-Box Evaluation Framework for LLM-Based DSM Generation, by Niels Potters and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: < prev | next > new | recent | 2026-07 Change to browse by: cs eess References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer?

) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle ( What is ? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

整合知识图谱与多语言学术语料，推动SSH领域自适应LLM研究

一项最新研究提出通过整合知识图谱和多语言学术语料库，构建适用于社会科学与人文学科（SSH）的领域自适应大语言模型。该论文题为《Integrating knowledge graphs and multilingual scholarly corpora for domain-adaptive LLMs in SSH》，由Adam Faci等六位研究人员共同完成，于2026年7月7日提交至arXiv预印本平台。论文目前提供PDF全文和HTML预览，相关数字对象标识符（DOI）正在通过DataCite登记中。该研究属于计算机科学范畴，旨在利用结构化知识图谱与多语种学术文献，提升大语言模型在特定学科的理解与推理能力，为跨学科人工智能应用提供了新方向。 #知识图谱 #多语言语料库 #大语言模型 #领域自适应 #SSH #arXiv #学术研究 #人工智能 #跨学科

SearchEyes论文提出多模态深度搜索智能新方法，通过搜索世界模拟实现前沿搜索能力

近日，一篇题为《SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation》的论文提交至预印本平台arXiv。该论文由Zhengbo Jiao等18位研究人员共同撰写，提出了一种通过模拟搜索世界来训练和评估多模态深度搜索智能的创新框架。研究聚焦于融合文本、图像等多种信息模态，在模拟环境中提升模型对复杂查询的深度理解与精准检索能力。该工作旨在突破传统搜索方法的局限，为下一代智能检索系统提供新思路，引起了学术界的广泛关注。 #多模态搜索 #深度搜索 #人工智能 #SearchEyes #arXiv #学术论文 #前沿科技 #智能检索