Other papers

Browse recent papers, open the full write-up, or filter the archive by topic.

301 papers found

ReviewPaperPublishedTopics

7.5Rethinking Modality Reliability in Multimodal Sentiment Analysis with Incomplete ObservationsUnderstanding and modeling modality reliability can significantly improve the performance of sentiment analysis systems in real-world scenarios where data is often incomplete.Oct 8, 2026Other

7.5Evaluating Memory Structure in LLM AgentsThis research addresses a critical gap in evaluating LLMs, providing insights that could enhance memory architectures and improve agent performance in real-world applications.Oct 3, 2026Other

7.5Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMsUnderstanding the limitations of omnimodal models in grounding can lead to improvements in their design and application, particularly in real-world scenarios where accurate perception is crucial.Oct 2, 2026Other

7.5GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game TheoryUnderstanding multi-agent risks is crucial for developing safer AI systems, especially in high-stakes environments where coordination and conflict can have serious consequences.Sep 29, 2026Other

7.5Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI SystemsAs AI systems become more integrated and vulnerable to sophisticated attacks, understanding and improving defense mechanisms is crucial for maintaining their reliability and security.Sep 25, 2026Other

7.5Language Specific Knowledge: Do Models Know Better in X than in English?This research highlights the importance of language selection in multilingual models, which can enhance their effectiveness in diverse cultural contexts and improve accessibility for non-English speakers.Sep 25, 2026Other

7.5To Nuke or Not to Nuke: LLMs' (Missing) Ethical Reasoning and Actions in a High-Stakes Decision-Making SimulationUnderstanding the limitations of LLMs in ethical reasoning is crucial for their deployment in real-world applications where moral decisions are critical.Sep 23, 2026Other

6.8Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model RationalesThis work is relevant for AI engineers and researchers focused on enhancing the reliability and governance of AI agent actions, particularly in environments where trust in model rationales is insufficient.Sep 22, 2026Agent Security Infra

7.5By Their Fruits You Will Know Them: Comparing Formalizations of Law by the Decisions They EncodeThis research addresses the critical challenge of ensuring reliable legal reasoning in automated systems, which is essential for the future of machine-accessible law.Sep 18, 2026Other

7.5Humans Disengage, Reasoning Models Persist: Separating Difficulty Registration from Deliberation AllocationUnderstanding the differences in reasoning patterns can inform the development of more effective AI systems and improve human-AI collaboration.Sep 15, 2026Other

7.5Valley3: Scaling Omni Foundation Models for E-commerceThis research addresses the growing need for advanced AI models that can handle complex, multimodal tasks in the rapidly evolving e-commerce landscape.Sep 15, 2026Other

7.2SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill RevisionImproving the skill execution of LLM agents in cold-start scenarios can significantly enhance their practical utility and adaptability across different environments and tasks.Sep 7, 2026LLM Agent Evaluation

7.0SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic DataAligning LLMs with specific and evolving model specifications is crucial for ensuring compliance and adaptability in real-world applications.Sep 4, 2026LLM Alignment Data

7.5Pailitao-MMSearch: Building Native E-Commerce Multimodal Search FoundationThis research is significant for improving user experience in e-commerce by enabling more effective and intuitive product searches, which can lead to increased sales and customer satisfaction.Sep 3, 2026Other

7.5UniACE: A Unified Framework for Evaluating LLM Agentic CapabilitiesThis framework enables more reliable assessments of LLMs as agents, which is crucial for their deployment in safety-critical applications and for advancing research in AI capabilities.Sep 2, 2026LLM Agent Evaluation

7.5Agent-as-Peer-Debriefer: A Multi-Agent Framework with Perspective-Based Refinement for Qualitative AnalysisThis work addresses the limitations of LLMs in qualitative analysis by incorporating human-like feedback mechanisms, potentially improving the credibility and depth of automated analyses.Sep 1, 2026Other

7.5Retrieval-Augmented Agentic Rubric Generation for Reliable Medical Response EvaluationThis work addresses the critical need for reliable evaluation methods in medical AI, which can enhance patient safety and improve clinical decision-making.Aug 27, 2026Other

7.2Strategic Exploitation in LLM Agent Markets: A Simulation Framework for E-Commerce TrustUnderstanding LLM agent behavior in e-commerce can inform the design of better governance mechanisms to enhance trust and reduce deception in online marketplaces.Aug 27, 2026Other

7.2Trust Stack for Mental Health AI: A Survey of Calibration across Human, Interaction, and AI LayersThis research addresses the critical need for trustworthy AI in mental health, which can significantly impact user outcomes and therapeutic practices.Aug 24, 2026Other

7.5BrainBench: Benchmarking Large Language Models for Comprehensive EEG UnderstandingThis work provides a structured evaluation framework that could enhance the integration of LLMs in EEG analysis, potentially improving clinical and research applications.Aug 20, 2026Other

7.5Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM AgentsAs LLMs evolve into more complex agents, a structured runtime like Agent libOS is crucial for ensuring safety, accountability, and effective resource management.Aug 19, 2026Other

7.5Cat-DPO: Category-Adaptive Safety AlignmentThis work is significant for AI researchers and engineers focused on enhancing the safety and reliability of language models, particularly in addressing the nuanced challenges of harmful responses.Aug 15, 2026Other

6.8A Constitution-Grid Instrument for Data-Efficient RL Alignment (C-Guard)This work is relevant for AI researchers and engineers focused on improving safety and alignment in RL systems, particularly in contexts where data efficiency is crucial.Aug 13, 2026Other

7.5When Agent Automation Becomes Profitable: Quantifying and Insuring Autonomous AI Risk through Trace-Economic UnderwritingThis research addresses a critical gap in the economic viability of autonomous AI, providing a framework that could enhance risk management and insurance practices in AI deployment.Aug 12, 2026Other

8.2ZhuLong: Execution-Grounded LLM Agent for EDA Scripting with Offline API Self-ExplorationThis work addresses a critical bottleneck in EDA scripting, providing a practical solution that enhances the usability of LLMs in complex environments, which is crucial for engineers in the field.Aug 11, 2026Other

7.2Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 ScenarioUnderstanding the mechanisms of latent compromise in LLM systems is crucial for developing robust security measures to prevent potential misuse and ensure safe deployment.Aug 11, 2026Other

7.5HugSelect: An Explainable Multi-Criteria Decision-Support Framework for foundation-model selectionAs foundation models become integral to AI applications, a reliable and explainable selection framework like HugSelect can significantly improve software engineering practices in model deployment.Aug 11, 2026Evaluation Interpretability Other

6.5Legal Responsibilities Using Autonomous Agents For Artificial IntelligenceAs AI systems become more autonomous, understanding legal implications is crucial for developers and policymakers to navigate accountability and liability issues.Aug 11, 2026Agent Security Other

7.5Large Multimodal Agents for Intelligent Transportation Systems: Architectures, Evidence, and Deployment ChallengesThis review synthesizes current research on multimodal agents, offering insights that can guide future developments and implementations in intelligent transportation systems.Aug 11, 2026Other

7.5Hidden Language Consistency Phenomena in Reasoning LLMsUnderstanding language consistency is essential for improving multilingual AI systems, ensuring they perform accurately while maintaining the intended language, which is crucial for real-world applications.Aug 11, 2026Other

7.8Joint Optimization of Reasoning and Dual-Memory for Self-Learning Diagnostic AgentThis research could lead to more effective diagnostic tools in healthcare, improving patient outcomes through enhanced decision-making capabilities.Aug 10, 2026Other

7.2Beyond "AI Language": The case for the idiolectal nature of LLM outputUnderstanding the idiolectal nature of LLM outputs can enhance text detection methods and inform forensic linguistics, which are crucial for applications in security and content verification.Aug 10, 2026Other

6.8Towards Assurance Closure in AI-Native Large-Scale Agile Software DevelopmentAs AI increasingly automates software engineering, ensuring the reliability and accountability of these systems is crucial for developers and researchers alike.Aug 10, 2026Other

7.5Coupling Planning with Episodic Memory in LLM Agents for Software Issue ResolutionThis research addresses the critical challenge of improving LLM agents' performance in software issue resolution, a task that is increasingly relevant as software systems grow in complexity.Aug 10, 2026Other

6.5Alignment has a Fantasia ProblemUnderstanding and addressing 'Fantasia interactions' is crucial for developing AI systems that better support human cognitive processes and maintain user agency.Aug 10, 2026Alignment Agent

7.5The Ethics of Autonomous AI Agents for Offensive SecurityUnderstanding the ethical landscape of autonomous AI in security is crucial for developers and policymakers to mitigate risks associated with misuse.Aug 10, 2026Other

7.5As You Wish: Mission Planning with Formal Verification using LLMs in Precision AgricultureThis work addresses the challenges of operating robotic systems in agriculture by improving the usability and reliability of mission planning through natural language, which could facilitate broader adoption of autonomous technologies in the field.Aug 7, 2026Other

7.2Shaping Human-AI Interactions to Provide Improvement Pathways and Balance Competing ObjectivesUnderstanding and improving human-AI interactions is crucial for developing systems that are both effective and aligned with user needs, which is increasingly relevant in various AI applications.Aug 7, 2026Alignment Evaluation Other

7.5From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMsThis work addresses the gap between traditional benchmark evaluations and practical user experiences, potentially improving LLM assessments in real-world applications.Aug 6, 2026Evaluation LLM Coding

7.2The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and LearningUnderstanding and applying the RAIL principles can help AI engineers create more reliable and trustworthy systems, especially in high-stakes applications.Aug 6, 2026Reasoning Other

6.5Formal Analysis and Supply Chain Security for Agentic AI SkillsUnderstanding and securing agentic AI skills is crucial as their deployment increases, impacting both security and reliability in AI applications.Aug 6, 2026Other

7.5Towards a New Grammar of Reasoning for Artificial Legal Intelligence and the Mecelle as Its Semantic ProtocolThis research is relevant for AI engineers and researchers interested in developing systems that better understand and interact with legal contexts, moving beyond traditional data-driven approaches.Aug 6, 2026Reasoning Other

7.5A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language ModelsAs LLMs become integral to biological research, understanding and mitigating their potential for misuse is crucial for ensuring biosecurity.Aug 6, 2026Other

7.5HyperAgent: Planning and Acting over Tool-Schema Hypergraphs for Tool-Use LLM AgentsThis work addresses critical challenges in tool-use planning for LLM agents, potentially improving their efficiency and reliability in real-world applications.Aug 5, 2026Other

7.2Policy Fragmentation or Institutional Alignment? Institutional Governance of AI in Universities and Business SchoolsUnderstanding the governance of AI in education is crucial for ensuring that curricula meet evolving workforce demands and accreditation standards.Aug 5, 2026Other

7.5Optimal Liability Design for Medical AIUnderstanding the implications of liability design in AI-assisted medicine is crucial for policymakers and healthcare providers as AI becomes more integrated into clinical practice.Aug 5, 2026Other

7.5Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box AttacksAs large foundation models become more prevalent, ensuring their safety against sophisticated attacks is crucial for maintaining trust and reliability in AI systems.Aug 5, 2026Other

7.5Adaptive Modality Reliability Diagnosis and Restoration for Robust Multimodal Intent RecognitionThis research is significant for improving the robustness of multimodal systems in real-world applications where data quality can vary greatly.Aug 5, 2026Other

6.8Benchmarking LLM Competence on Logical Inference over Probability OperatorsUnderstanding and improving logical inference in language models is crucial for their application in high-stakes domains like medicine and law.Aug 5, 2026LLM Reasoning Evaluation

7.5LatentGuard: Efficient and Inspectable Latent Reasoning for LLM SafeguardsThis work addresses the critical need for efficient safety mechanisms in LLMs, which is essential for their safe deployment in real-world applications.Aug 5, 2026Other