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 .

What Actually Works for Spacecraft Fault-Tolerant Control: An Honest Settled-Gate Benchmark of Learned and Classical Methods

Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Alireza Shojaei [ view email ] [v1] Wed, 24 Jun 2026 04:08:39 UTC (32 KB) Full-text links: Access Paper: View a PDF of the paper titled What Actually Works for Spacecraft Fault-Tolerant Control: An Honest Settled-Gate Benchmark of Learned and Classical Methods, by Alireza Shojaei View PDF HTML (experimental) TeX Source view license Current browse context: < prev | next > new | recent | 2026-06 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 Explore

r 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 .

Agentic Knowledge Tracing: A Multi-Agent LLM Architecture for Stealth Assessment of Financial Literacy in Serious Games

Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Gabriel Santos [ view email ] [v1] Wed, 24 Jun 2026 03:43:59 UTC (5,816 KB) Full-text links: Access Paper: View a PDF of the paper titled Agentic Knowledge Tracing: A Multi-Agent LLM Architecture for Stealth Assessment of Financial Literacy in Serious Games, by Gabriel Santos and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: < prev | next > new | recent | 2026-06 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 Bibliograp

hic 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 .

Omni-Perception Policy Optimization for Multimodal Emotion Reasoning

Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Zhiyuan Han [ view email ] [v1] Wed, 24 Jun 2026 02:43:26 UTC (7,878 KB) Full-text links: Access Paper: View a PDF of the paper titled Omni-Perception Policy Optimization for Multimodal Emotion Reasoning, by Zhiyuan Han and 8 other authors View PDF HTML (experimental) TeX Source view license Current browse context: < prev | next > new | recent | 2026-06 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 Paper

s ( 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 .

Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty

Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Antonis Antoniades [ view email ] [v1] Tue, 23 Jun 2026 21:44:08 UTC (6,269 KB) Full-text links: Access Paper: View a PDF of the paper titled Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty, by Antonis Antoniades and 8 other authors View PDF HTML (experimental) TeX Source view license Current browse context: < prev | next > new | recent | 2026-06 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 Bibliographi

c 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 .

To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi

Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Jungseob Lee [ view email ] [v1] Tue, 23 Jun 2026 21:34:23 UTC (281 KB) Full-text links: Access Paper: View a PDF of the paper titled To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi-Agent RAG, by Jungseob Lee and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: < prev | next > new | recent | 2026-06 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 .

Transferability for General Reasoning: An Automated Curriculum for Multi

Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Yongjin Yang [ view email ] [v1] Tue, 23 Jun 2026 21:10:29 UTC (670 KB) Full-text links: Access Paper: View a PDF of the paper titled Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR, by Yongjin Yang and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: < prev | next > new | recent | 2026-06 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 To

ggle 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 .

研究提出基于等级分的棋手风格嵌入模型

一篇名为《基于等级分条件残差移动模型的人类国际象棋棋手风格嵌入》的论文在arXiv上发布。该研究由Jason Carlson完成，旨在通过等级分（Elo rating）条件残差移动模型，从人类对局数据中解耦并学习棋手的个性化风格嵌入。传统方法通常将棋手水平与风格混合建模，而新模型通过条件化等级分，分离出风格特征，有助于更精细地分析人类棋手的决策模式与棋风差异。该工作为棋类AI与人类行为理解提供了新视角，相关代码与数据已开放。 #arXiv #国际象棋 #棋手风格 #AI #机器学习 #论文

TRUSTMEM：为长时记忆LLM智能体学习可信记忆巩固方法

研究人员提出名为TRUSTMEM的新型框架，旨在解决大语言模型（LLM）智能体在长期记忆中存在的可信度问题。该框架通过强化学习机制，使智能体能够自主筛选、整合和巩固重要信息，避免存储错误或无关记忆。实验表明，TRUSTMEM在多个长时交互任务中显著提升了记忆的准确性和模型决策的可靠性，为构建更安全、可信的自主智能体提供了新思路。论文作者来自相关研究机构，目前该工作已在arXiv上公开，并将进一步探索与知识图谱的结合。 #AI #LLM #长期记忆 #可信人工智能 #智能体 #机器学习 #记忆巩固

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

临床医生否决权

一篇题为《临床医生的否决权：自主AI处方中的信任、责任与不确定性》的学术论文于2026年6月提交至arXiv预印本平台。该研究由Eileanor LaRocco等七位学者共同完成，聚焦于人工智能在医疗处方领域自主决策时面临的临床医生角色困境。论文深入探讨了在AI提出治疗方案后，医生行使最终否决权的法律与伦理基础，分析了责任归属、信任机制以及在不确定医疗情境下的决策流程。研究指出，尽管AI辅助诊断和处方能力日益增强，但保留医生的最终审查与否决权对于防范医疗风险、维护患者安全及厘清法律责任至关重要。该工作为构建人机协作的智能医疗系统提供了理论框架，并呼吁政策制定者关注AI处方中的透明度与问责制。 #AI医疗 #临床决策 #责任归属 #信任机制 #学术论文 #arXiv #人工智能伦理 #医疗法规

Beyond Shapley: 非对称Shapley值高效计算方法获突破

一篇题为《Beyond Shapley: Efficient Computation of Asymmetric Shapley Values》的学术论文近日在arXiv预印本平台发布。该研究由Ezequiel Companeetz等人完成，聚焦博弈论中经典Shapley值的扩展与高效计算。传统的Shapley值在公平分配贡献时假设对称性，而实际场景中变量间的交互往往是非对称的。论文提出了一种能够高效计算非对称Shapley值的算法，有望在机器学习可解释性、特征重要性评估、合作博弈等应用领域提升计算效率与实用性。目前该论文已提供PDF全文及实验代码链接，供研究人员复现与验证。 #博弈论 #Shapley值 #非对称 #高效计算 #机器学习可解释性 #arXiv #学术论文 #AI #算法

视觉-语言模型是否像人类一样搜索？推理标记作为经典视觉搜索范式中的反应时间类比

一项发表于arXiv的新研究探讨了视觉-语言模型（VLM）在视觉搜索任务中的表现是否与人类相似。研究由Farahnaz Wick等人完成，创新性地将模型生成的推理标记（reasoning tokens）数量类比为人类的反应时间（reaction time），并在经典视觉搜索范式下进行对比实验。结果表明，VLM在部分搜索策略上展现出类似人类的行为，例如对目标特征的关注模式，但在复杂场景下仍存在显著差异。该工作为理解大模型如何模拟人类认知过程提供了新视角，并可能推动更仿生的AI视觉系统设计。 #视觉语言模型 #视觉搜索 #推理标记 #反应时间 #AI认知 #arXiv #机器学习

用分类策略检索诊断与缓解代理说服中的复合故障

近日，一篇发表在arXiv上的研究提出了一种通过分类策略检索来诊断与缓解代理说服系统中复合故障的新方法。该研究由Pradyumna Narayana等学者完成，聚焦于多步交互中代理说服策略逐渐失效的问题。研究团队构建了分类策略库，对不同类型的失败模式进行结构化分析，并设计了相应的检索与缓解机制。实验表明，该方法能够有效识别故障根源，显著提升代理在复杂说服场景中的稳定性和成功率，为构建更可靠的自主对话系统提供了新思路。 #arXiv #人工智能 #代理系统 #说服技术 #故障诊断 #策略检索 #AI安全 #多步交互

Project Auto-World

科研团队提出名为“Auto-World”的新项目，旨在为神经关系推理器构建自动化基准测试框架。当前，评估这类推理模型通常依赖手动设计的任务和数据集，过程繁琐且难以扩展。Auto-World通过自动化生成多样化场景与问题，全面测试模型在关系推理、逻辑演绎等能力上的表现。该方法有望简化评估流程，提升基准测试的覆盖度与公平性，推动神经关系推理领域的发展。相关论文已在预印本平台发布，并开源实验代码。 #AI #神经推理 #基准测试 #自动化 #机器学习 #论文 #arXiv