Other papers

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

267 papers found

ReviewPaperPublishedTopics

7.5Beyond Memory: A Templated Substrate for Heterogeneous Collaborative Knowledge Work with LLM AgentsThis work addresses a critical gap in knowledge retention in research, which can significantly improve future collaborative efforts and reduce redundant work.Jul 30, 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.Jul 30, 2026Agent Security Infra

6.5Adversarial Pragmatics for AI Safety Evaluation: A Diagnostic Framework and Seed Benchmark for Language-Mediated ControlUnderstanding and diagnosing safety issues in language models is crucial for developing reliable AI systems, especially in ambiguous or adversarial contexts.Jul 30, 2026LLM Safety Evaluation

6.8Why Public Service AI Governance Frameworks Risk Failing in the Age of General-Purpose AI: Lessons from PolicingUnderstanding the limitations of current AI governance frameworks is crucial for AI engineers and researchers to ensure safe and responsible deployment of general-purpose AI in public services.Jul 30, 2026Safety Survey Other

6.5CogArena: A Multimethod Evaluation of Cognitive Ability Structure in Large Language ModelsUnderstanding cognitive ability structures in LLMs can enhance model evaluation and inform future developments in AI.Jul 30, 2026Other

6.5The Possibility of Artificial Intelligence Becoming a Subject and the Alignment ProblemUnderstanding and preparing for AGI as autonomous entities could fundamentally change AI alignment strategies and human-AI interactions.Jul 29, 2026Alignment Agent Other

7.5Structured Scaling of AI Discovery Across Diverse Scientific DomainsThis work provides a practical framework for researchers and engineers to improve the efficiency and effectiveness of scientific discovery processes using language models.Jul 29, 2026Other

6.8Separating Capability from Permission: A Governance Framework for Agentic AI Autonomy LevelsUnderstanding and managing the distinction between what AI systems can do and what they are allowed to do is crucial for safe and effective deployment in real-world applications.Jul 28, 2026Agent Safety Other

7.5WIRE: Profiling Witnessed Within-Policy Instruction Collisions in LLM AgentsUnderstanding and resolving instruction conflicts in LLMs is crucial for improving their reliability and effectiveness in real-world applications.Jul 28, 2026Other

6.8Regulating for AI LegitimacyUnderstanding AI legitimacy is vital for developing systems that are not only technically aligned but also socially accepted and trusted, which is crucial for widespread adoption and governance.Jul 28, 2026Alignment Other

7.2Between Suppression and Collapse: Evaluating Narrative Unlearning with LENSUnderstanding narrative unlearning is crucial for improving the reliability of language models and mitigating the spread of disinformation.Jul 28, 2026Other

7.5Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of PersonasUnderstanding and manipulating reasoning processes in LLMs can lead to more accurate and reliable AI systems, which is crucial for practical applications.Jul 28, 2026Other

6.8Regulating autonomous and agentic AIAs AI systems become more autonomous, understanding how to effectively regulate them is crucial for ensuring safety and accountability in their deployment.Jul 24, 2026Other

7.5Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM AgentsUnderstanding silent failures in LLM agents is crucial for improving their reliability and safety in real-world applications, particularly in sensitive domains.Jul 23, 2026Other

7.5The Story Shapes the Agent: Narrative Priors in LLM BehaviorUnderstanding the impact of narrative on LLM behavior can enhance the design of AI systems for more effective task performance across varied contexts.Jul 22, 2026Other

6.8"I understand your perspective": LLM Persuasion through the Lens of Communicative Action TheoryUnderstanding LLMs' persuasive capabilities can enhance their design for applications requiring nuanced communication, such as negotiation or customer service.Jul 22, 2026LLM Evaluation

7.5Hazard or Anomaly? Evaluating VLMs for Understanding Dangers and DiscrepanciesUnderstanding the difference between hazards and anomalies is crucial for improving the reliability of VLMs in safety-critical applications, which can directly impact emergency decision-making.Jul 22, 2026Other

6.8Lomekwi: Resource-Bounded Tool Discovery in LLM AgentsThis research could inform the development of more effective LLM agents by addressing the complexities of tool discovery, which is crucial for advanced AI applications.Jul 21, 2026Other

6.5Towards AI epidemiology: a measurement standardisation framework for prospective risk detectionThis framework could enhance the reliability and governance of AI systems by providing a structured approach to evaluate expert-AI interactions.Jul 21, 2026Alignment Evaluation Other

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.Jul 21, 2026Other

7.2AI Contagion in Social NetworksUnderstanding AI's impact on social networks is crucial for developing effective regulatory measures to mitigate misinformation and enhance collective knowledge stability.Jul 21, 2026Other

7.5What Do They See? Interpreting Complex Road Scenarios Through the Eyes of Vision-Language-Action Models for Safe and Trustworthy Autonomous Vehicle LearningThis research addresses the critical need for interpretability in autonomous vehicle systems, enhancing safety and trust in AI-driven technologies.Jul 21, 2026Other

6.8Digital Pantheon: Simulating and Auditing Coalition Formation with LLM AgentsUnderstanding coalition dynamics through simulation can aid political scientists and policymakers in exploring party compatibility and negotiation strategies before real-world applications.Jul 20, 2026LLM Agent Alignment

7.5Scaling Behavior Foundation Model for Humanoid RobotsImproving humanoid robot control is crucial for developing generalist embodied agents capable of operating in diverse environments, which has significant implications for robotics applications.Jul 18, 2026Other

7.5Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship AttributionAs LLMs become more prevalent, effective detection of their outputs is crucial for maintaining content integrity and accountability in various applications.Jul 18, 2026Other

7.2Align AI to Dynamic Human-AI WorkflowsUnderstanding and implementing dynamic alignment can enhance the effectiveness of human-AI collaboration, making AI systems more responsive to real-world complexities.Jul 18, 2026Alignment Other

6.5Unsafe at any AUC: Unlearned Lessons from Sociotechnical Disasters for Responsible AIAI engineers and researchers should care because understanding systemic risks and organizational dynamics can prevent future AI-related failures.Jul 18, 2026Safety Survey Other

7.2Enhancing Small Language Models Reasoning through Knowledge Graph GroundingThis research addresses the limitations of small language models in reasoning tasks, offering a more sustainable alternative to large models while highlighting the challenges of symbolic grounding.Jul 18, 2026Other

7.2Multimodality as Supervision: Self-Supervised Specialization to the Test Environment via MultimodalityThis research could significantly enhance the efficiency of training models for specific applications, particularly in robotics, by minimizing the need for extensive pre-training on diverse datasets.Jul 18, 2026Other

7.5Contextualized Evaluation of Vision Language Models through Dynamic, Multi-turn InteractionsThis research addresses the critical gap between benchmark evaluations and real-world applications, providing insights into model vulnerabilities that could inform future improvements in MLLMs.Jul 18, 2026Other

7.5SafeRelBench: A Spatial-Relation-Aware Benchmark for Process-Level Safety in VLM-Driven Embodied AgentsThis research addresses a critical gap in safety evaluations for embodied agents, emphasizing the need for improved safety assessments in real-world applications.Jul 18, 2026Other

7.5Multi-Head Latent Control: A Unified Interface for LLM Agent Decision MakingThis work addresses the critical need for efficient decision-making in LLMs, potentially reducing costs and improving performance in multi-model systems.Jul 17, 2026Other

7.5Scaling Evaluation-time Compute with Reasoning Models as EvaluatorsThis research addresses the growing challenge of evaluating increasingly sophisticated language model outputs, providing a potential method to improve their assessment and effectiveness in practical applications.Jul 17, 2026Other

7.5Linear representations of grammaticality in neural language modelsUnderstanding how NLMs encode grammaticality can enhance our insights into their syntactic knowledge and improve evaluations of their linguistic competence.Jul 17, 2026Evaluation Other

6.8Post-Deployment Accountability in AI Governance: A Cross-Regulatory Empirical Analysis of AI IncidentsUnderstanding and improving AI governance is crucial for ensuring accountability and compliance in high-stakes AI deployments, which is essential for both developers and regulators.Jul 16, 2026Safety Other

5.5How LLMs Might ThinkUnderstanding the nature of LLM 'thinking' could influence how we interpret their outputs and guide future AI development.Jul 16, 2026LLM Reasoning Interpretability

7.5When Are Sparse Feature Interventions Actually Localized? Matched Evaluation for SAE-Based Safety ControlUnderstanding the limitations and effective regimes of SAE-based safety interventions is crucial for developing reliable AI systems that prioritize safety.Jul 14, 2026Other

7.2MorphologyFM: A Foundation Model for Morphology-Aware Representation Learning from ECG and Pulse Oximetry WaveformsUnderstanding and predicting physiological conditions from ECG and SpO2 waveforms can enhance patient monitoring and care in critical settings.Jul 14, 2026Multimodal Other

7.2LOGOS: A Living Logic for AI Agent Teams That Evolve With HumansThis framework addresses the critical challenge of controlling the evolution of AI agents, ensuring they remain aligned with human values and objectives as they learn and adapt.Jul 14, 2026Other

7.5PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model MergingThis work addresses a significant gap in multimodal pre-training, potentially improving the performance and efficiency of large language models in diverse applications.Jul 14, 2026Other

8.2Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and EditingThis research addresses critical limitations in existing multimodal models, offering a scalable solution for complex interactions that could significantly enhance applications in AI-driven dialogue systems.Jul 11, 2026Other

7.5Who Broke the System? Failure Localization in LLM-Based Multi-Agent SystemsUnderstanding and diagnosing failures in multi-agent systems is crucial for enhancing their reliability and effectiveness in complex problem-solving scenarios.Jul 10, 2026Other

7.5Evaluating the Generalizability of Foundation Models for Extreme Environmental Events: Case Study of California Wildfire PM2.5Understanding the limitations of foundation models in extreme environmental conditions is crucial for public health forecasting and resource allocation during wildfire events.Jul 10, 2026Other

8.2A safety-oriented hypothetico-deductive framework for AI-assisted differential diagnosisThis research addresses critical safety concerns in medical diagnostics, providing a framework that could significantly reduce diagnostic errors in acute care settings.Jul 10, 2026Other

7.5Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical ReasoningThis work is crucial for AI researchers and engineers aiming to develop reliable AI systems that meet clinical requirements and improve patient care.Jul 10, 2026Other

7.5Informing AI Policy Assessment using Large-Scale Simulation of InterventionsThis research provides a structured framework for policymakers to prioritize AI governance strategies effectively, addressing the urgent need for informed decision-making in AI policy.Jul 9, 2026Other

7.2HARC: Coupling Harmfulness and Refusal Directions for Robust Safety AlignmentImproving the safety alignment of language models is crucial for preventing harmful outputs and ensuring reliable AI systems, making this research relevant for AI safety and deployment.Jul 9, 2026LLM Alignment Safety

7.5Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data GenerationUnderstanding which language models serve as effective teachers can enhance the quality of synthetic data generation, particularly for less-resourced languages, thereby improving multilingual model performance.Jul 8, 2026Other

7.5Agentic AI for Commercial Insurance Underwriting with Adversarial Self-CritiqueThis research addresses critical safety and reliability concerns in AI applications for regulated industries, making it relevant for both practitioners and researchers focused on responsible AI deployment.Jul 8, 2026Other

7.5Decision Protocols in Multi-Agent Large Language Model ConversationsThis research addresses the challenges of scaling LLMs by exploring how multi-agent systems can enhance task performance, which is crucial for practical applications in AI.Jul 8, 2026Other