Other papers

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

184 papers found

ReviewPaperPublishedTopics

7.2Neuro-Symbolic Agents for Regulated Process Automation: Challenges and Research AgendaAs LLM-based agents increasingly enter regulated industries, ensuring compliance and reducing errors is critical for both safety and efficiency.Jun 12, 2026Other

6.5If LLMs Have Human-Like Attributes, Then So Does Age of Empires IIThis work prompts researchers to reconsider the criteria for attributing human-like qualities to AI systems, which could influence future AI development and evaluation.Jun 12, 2026Other

7.5Agentic Large Language Models for Automated Structural Analysis of 3D Frame SystemsThis work could significantly streamline structural engineering processes, making them more efficient and accessible through natural language interfaces.Jun 12, 2026Other

6.8Definitional alignment before capability alignment: a Design-Science framework for adjudicating claims about AGIThis work is relevant for researchers and engineers as it provides a structured approach to navigate the complex landscape of AGI definitions, which is crucial for effective communication and governance in AI development.Jun 12, 2026Alignment Evaluation Other

7.5Polar: A Benchmark for Evaluating Political Bias in LLMsUnderstanding political bias in LLMs is crucial for ensuring fairness and accuracy in AI applications, especially in multilingual and cross-cultural settings.Jun 12, 2026Other

7.2A Study of Belief Revision Postulates in Multi-Agent Systems (Extended Version)Understanding belief revision in multi-agent systems is crucial for developing more sophisticated AI systems that can reason and adapt in dynamic environments.Jun 12, 2026Other

7.5Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using AgentsAs LLM-based agents become more capable, understanding and mitigating their safety risks in complex interactions is crucial for responsible deployment in real-world applications.Jun 12, 2026Other

6.8A Survey of Reasoning and Agentic Systems in Time Series with Large Language ModelsThis survey organizes and clarifies the landscape of time series reasoning, which is crucial for researchers and practitioners aiming to develop robust systems that can understand and act on dynamic data.Jun 11, 2026Other

7.5T2MM: An LLM Supported Architecture For Inquiry-Based ModelingThis research addresses a gap in educational tools by providing a more interactive approach to model construction, which could significantly improve learning outcomes in science education.Jun 11, 2026Other

7.5Models That Know How Evaluations Are Designed Score SaferUnderstanding evaluation meta-knowledge is crucial for designing reliable AI safety assessments and interpreting their results accurately.Jun 11, 2026Other

7.5Tabular Foundation Models for Clinical Survival Analysis via Survival-Aware AdaptationThis work addresses a critical gap in survival analysis by leveraging advanced machine learning techniques, potentially improving clinical decision-making in critical care settings.Jun 11, 2026Other

7.5The Governance of Human-LLM Interaction: Safety Gating, Civility Steering, and Affective Default Lock-InUnderstanding the governance of LLM interactions is crucial for ensuring user safety and autonomy in high-stakes environments.Jun 9, 2026Other

7.5AgentTrust: A Self-Improving Trust Layer for AI-Agent ActionsAs AI agents increasingly perform critical tasks, a robust trust mechanism is essential to ensure safe and reliable operations, making this research highly relevant for developers and researchers in AI safety and security.Jun 9, 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.Jun 9, 2026Other

7.5AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation ModelsImproving spatial reasoning in AI models is crucial for applications in robotics, navigation, and interactive systems, making this research relevant for advancing multimodal AI capabilities.Jun 9, 2026Other

7.2"I understand your perspective": LLM Persuasion and Sycophancy through the Lens of Communicative Action TheoryUnderstanding LLMs' persuasive abilities is crucial for developing ethical AI systems and mitigating potential manipulation in human-AI interactions.Jun 9, 2026Other

7.5Re-imagining ISO 26262 in the Age of Autonomous Vehicles: Enhancing Controllability through Transferability and PredictabilityAs autonomous vehicles become more prevalent, adapting safety standards like ISO 26262 is crucial for ensuring their safe integration into society.Jun 8, 2026Other

6.8Agentic Physical AI toward a Domain-Specific Foundation Model for Energy Systems: A Case Study on Nuclear Reactor ControlThis work is relevant for AI researchers and engineers interested in applying AI to safety-critical systems, offering insights into domain-specific model development and reliability in controlled simulations.Jun 8, 2026Agent Safety Architecture

7.2Measuring Agents in ProductionThis research provides valuable insights into the practical deployment of LLM-based agents, highlighting common practices and challenges that can inform future development and research.Jun 8, 2026Other

7.5Sycophantic Praise: Evaluating Excessive Praise in Language ModelsUnderstanding and calibrating praise in language models can improve their alignment with user expectations and enhance their utility in social and interpretive contexts.Jun 8, 2026Other

6.8Insurance of Agentic AIAs AI systems become more autonomous, understanding how to insure their risks is crucial for mitigating potential liabilities and ensuring safe deployment.Jun 6, 2026Agent Security Safety

7.5From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM AgentsThis work addresses critical safety concerns in LLM applications by proposing a novel approach to risk management that preserves task integrity while mitigating threats.Jun 6, 2026Other

7.5LoopFM: Learning frOm HistOrical RePresentations of Foundation Model for RecommendationThis work addresses a critical limitation in knowledge distillation, potentially improving recommendation systems' performance in real-world applications.Jun 5, 2026Other

6.8DAR: Deontic Reasoning with Agentic HarnessesThis work addresses a significant challenge in applying LLMs to complex legal reasoning tasks, potentially improving their utility in real-world applications.Jun 5, 2026Other

7.5Streaming Communication in Multi-Agent ReasoningThis work addresses critical efficiency and effectiveness challenges in multi-agent systems, making it relevant for researchers and engineers focused on optimizing AI communication and reasoning.Jun 5, 2026Other

6.8Toward AI That Understands Self and Others: A World-Model Theory of Cognitive Diversity and AlignmentThis research could inform the design of AI systems that respect diverse cognitive perspectives while maintaining effective communication and error detection.Jun 3, 2026Other

7.5Agent libOS: A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM AgentsAs LLMs evolve into more complex agents, a structured runtime like Agent libOS is crucial for ensuring safety, accountability, and effective resource management.Jun 3, 2026Other

7.8SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill RevisionThis work addresses the challenge of cold-start skill development for LLM agents, providing a systematic approach that could significantly improve agent performance in real-world applications.Jun 3, 2026LLM Agent Evaluation

7.5Bridging the Last Mile of Time Series Forecasting with LLM AgentsThis research addresses a critical gap in time series forecasting by emphasizing the importance of contextual factors, making forecasts more applicable in real-world business scenarios.Jun 2, 2026Other

7.5Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM PromptsAs LLMs are increasingly deployed in critical applications, understanding and mitigating their vulnerabilities to adversarial attacks is essential for ensuring reliability and safety.Jun 2, 2026Other

7.5TrustLDM: Benchmarking Trustworthiness in Language Diffusion ModelsUnderstanding trustworthiness in LDMs is crucial for developing safer AI systems, especially as these models gain prominence in language processing tasks.Jun 2, 2026Other

7.2Algorithmic Authority and the Clinical Standard of CareAs AI becomes more prevalent in healthcare, understanding its implications on clinical standards and liability is crucial for both practitioners and developers.Jun 2, 2026Other

7.5CAREAgent: Clinical Agent with Structured Reasoning and Tool-Integrated for Order GenerationThis research addresses a critical gap in clinical decision-making by improving the translation of medical decisions into actionable orders, which is essential for effective healthcare delivery.Jun 2, 2026Other

6.8Acting with AI: An Interaction-Based Framework for Agentic Tort LiabilityUnderstanding and addressing liability in AI-related incidents is crucial for legal clarity and the responsible deployment of AI systems.Jun 2, 2026Agent Other

7.5Post-Training LLMs as Better Decision-Making Agents: A Regret-Minimization ApproachImproving LLMs' decision-making abilities is crucial for their effective deployment in dynamic environments, making this research relevant for both practical applications and further theoretical exploration.Jun 1, 2026Other

7.5Side-by-side Comparison Amplifies Dialect Bias in Language ModelsUnderstanding and mitigating dialect bias in language models is crucial for ensuring fairness in AI applications, especially in high-stakes decision-making contexts.Jun 1, 2026Other

6.8Rationalize: Shared Semantic Reasoning for Human-AI AlignmentThis framework could facilitate better collaboration between humans and AI, making AI systems more interpretable and aligned with human intentions.Jun 1, 2026Other

7.5XLGoBench: Detecting cross-lingual skill gaps with algorithmic tasksUnderstanding cross-lingual skill gaps is crucial for improving the performance and fairness of language models in multilingual applications.Jun 1, 2026Other

7.5Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent SystemsThis research addresses the challenges of improving multi-agent systems in real-world applications, potentially leading to more reliable and scalable solutions.May 29, 2026Other

7.5Archon: A Unified Multimodal Model for Holistic Digital Human GenerationThis research addresses a significant challenge in digital human generation, which is crucial for applications in virtual reality, gaming, and interactive media.May 29, 2026Other

7.5UA-Legal-Bench: A Benchmark for Evaluating Large Language Models on Ukrainian Legal ReasoningThis benchmark addresses a significant gap in legal NLP by focusing on non-English languages, which is crucial for developing robust AI systems that can operate in diverse legal environments.May 29, 2026Other

7.5Provably Secure Agent GuardrailAs AI systems gain more autonomy, ensuring their security against complex attacks is crucial for safe deployment in real-world applications.May 29, 2026Other

7.5Indexing the Unreadable: LLM-Native Recursive Construction and Search of Service TaxonomiesThis work is relevant for AI engineers and researchers focusing on improving LLM efficiency and retrieval accuracy in complex service environments, which is crucial for the evolving Internet of Agents.May 29, 2026Other

7.5Human-Guided Harm Recovery for Computer Use AgentsAs AI agents increasingly interact with real systems, effective harm recovery mechanisms are crucial for ensuring safety and user trust.May 29, 2026Other

7.2Aligned but Fragile: Enhancing LLM Safety Robustness via Zeroth-Order OptimizationUnderstanding and enhancing the robustness of safety alignment in LLMs is crucial for developing safer AI systems that can withstand various perturbations without compromising their utility.May 29, 2026Other

7.5KVoiceBench, KOpenAudioBench, and KMMAU: Agent-Driven Korean Speech Benchmarks for Evaluating SpeechLMsThis work provides essential resources for assessing the performance of speech models in Korean, a language often overlooked in multilingual evaluations, thereby promoting inclusivity in AI research.May 28, 2026Other

6.8A Multi-dimensional Framework for Evaluating Generalization in EEG Foundation ModelsUnderstanding EEG model performance in low-resource settings is crucial for practical applications in neurotechnology and clinical fields.May 28, 2026Evaluation Benchmark Other

7.5SARAD: LLM-Based Safety-Aware Hybrid Reinforcement Learning with Collision Prediction for Autonomous DrivingThis research addresses critical safety challenges in autonomous driving, potentially leading to more reliable and efficient decision-making systems in real-world applications.May 28, 2026Other

7.5When Context Flips, Safety Breaks: Diagnosing Brittle Safety in Aligned Language ModelsUnderstanding and addressing brittle safety is crucial for the deployment of reliable AI systems, particularly in high-stakes applications where safety is paramount.May 28, 2026Other

6.8Tackling Multimodal Learning Challenges with Mixture-of-Expert: A SurveyThis survey provides a structured overview of MoE's potential in multimodal contexts, highlighting critical areas for future research that could improve model efficiency and effectiveness.May 28, 2026Other