Agent papers

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

260 papers found

ReviewPaperPublishedTopics

7.0Multi-Modal Agents for Power Distribution Defect Detection: An Evaluation of Foundation ModelsUnderstanding how multimodal foundation models can be applied to industrial defect detection could enhance automation and reliability in critical infrastructure maintenance.Jun 12, 2026Agent Multimodal Evaluation

7.2The Containment Gap: How Deployed Agentic AI Frameworks Fail Public-Facing Safety RequirementsAs agentic AI systems are increasingly used in sensitive public domains, ensuring their safety and reliability is crucial to prevent harmful outcomes.Jun 12, 2026Agent Safety Security

7.0LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem DiagnosisThis research is relevant for AI engineers and researchers interested in improving the robustness and accuracy of LLMs in technical problem-solving contexts, particularly in reducing biases introduced by user assumptions.Jun 12, 2026LLM Agent Reasoning

6.8Intelligence as Managed Autonomy: Failure, Escalation, and Governance for Agentic AI SystemsUnderstanding and managing AI system failures is crucial for developing reliable and safe autonomous systems, especially in critical domains like healthcare and robotics.Jun 12, 2026Agent Safety Architecture

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

7.2Parthenon Law: A Self-Evolving Legal-Agent FrameworkThis framework could significantly improve the efficiency and reliability of legal-domain LLM agents, making them more practical for real-world legal tasks.Jun 12, 2026LLM Agent Architecture

6.8Exploration Structure in LLM Agents for Multi-File Change LocalizationUnderstanding and improving how AI agents localize software changes can enhance the efficiency and accuracy of software maintenance and development processes.Jun 11, 2026LLM Agent Coding

7.2Multi-Agent Reasoning with Adaptive Worker Allocation for Stance DetectionThis approach could improve the robustness and accuracy of stance detection in complex and nuanced text, which is crucial for applications like sentiment analysis and opinion mining.Jun 11, 2026LLM Agent Reasoning

7.5MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence ReasoningThis work addresses the challenge of effectively utilizing long-tail events in social intelligence tasks, which is crucial for improving AI's understanding of nuanced social interactions.Jun 11, 2026LLM Agent Reasoning

7.2Agents All the Way Down; A Methodology for Building Custom AI Agents from Substrate to ProductionThis methodology could streamline the process of creating tailored AI agents, making it easier for engineers to implement specialized solutions in various applications.Jun 11, 2026Agent Coding

6.8AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively VulnerableUnderstanding the strengths and weaknesses of AI coding agents in social science can guide their deployment and highlight areas needing improvement, particularly in mitigating interpretive biases.Jun 11, 2026LLM Agent Evaluation

6.8Catching One in Five: LLM-as-Judge Blind Spots in Production Multi-Turn Transaction AgentsUnderstanding the limitations of LLM-based evaluations is crucial for improving the reliability and effectiveness of conversational agents in real-world applications.Jun 10, 2026LLM Agent Evaluation

6.8The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent MisalignmentAs AI systems increasingly rely on multi-agent interactions, ensuring alignment among agents is crucial for reliable decision-making and task execution.Jun 10, 2026Agent Alignment Evaluation

7.2Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and EvaluationAs LLM agents become more integrated into software systems, understanding their security vulnerabilities and defenses is crucial for safe deployment and operation.Jun 10, 2026LLM Agent Security

7.5BadRobot: Jailbreaking Embodied LLM Agents in the Physical WorldUnderstanding and mitigating the risks associated with embodied AI systems is crucial for ensuring their safe deployment in real-world applications.Jun 10, 2026LLM Agent Security

6.8The Confident Liar: Diagnosing Multi-Agent Debate with Log-Probabilities and LLM-as-JudgeUnderstanding the alignment between confidence signals and reasoning quality can improve the evaluation and reliability of multi-agent debate systems, which are crucial for applications requiring complex decision-making and reasoning.Jun 10, 2026LLM Agent Reasoning

7.2Causal Agent Replay: Counterfactual Attribution for LLM-Agent FailuresUnderstanding and attributing failures in LLM agents is crucial for improving their reliability and safety, making this work relevant for AI engineers and researchers focused on agent robustness.Jun 9, 2026LLM Agent Interpretability

7.5Oversight Has a Capacity: Calibrating Agent Guards to a Subjective, Fatiguing HumanUnderstanding the dynamics of human oversight in AI systems is crucial for developing safer and more effective agent behaviors, especially as they take irreversible actions.Jun 9, 2026Agent Safety

6.8Symbolic Reasoning Frameworks Modulate LLM Risk Aversion in Multi-Agent Strategic SettingsUnderstanding how symbolic reasoning frameworks affect language model behavior in strategic settings could inform the design of more effective AI agents in complex environments.Jun 9, 2026LLM Agent Reasoning

7.2Don't Make the LLM Read the Graph: Make the Graph ThinkUnderstanding how belief graphs can improve LLM performance in cooperative reasoning tasks could lead to more effective AI systems in complex, multi-agent environments.Jun 8, 2026LLM Agent Reasoning

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

7.2Lean4Agent: Formal Modeling and Verification for Agent Workflow and TrajectoryFormal verification of agent workflows can enhance the reliability and robustness of AI systems, which is crucial for deploying them in real-world applications.Jun 8, 2026LLM Agent Reasoning

7.5Will the Agent Recuse Itself? Measuring LLM-Agent Compliance with In-Band Access-Deny SignalsAs LLM agents take on more responsibilities, establishing mechanisms for compliance with access controls is crucial for safe and effective deployment in real-world applications.Jun 6, 2026LLM Agent Security

7.2Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI AgentsThis work is relevant for AI engineers and researchers focused on improving the reliability and compliance of AI systems in enterprise settings, addressing key limitations of current LLMs.Jun 6, 2026LLM Agent Reasoning

6.8Agent Memory: Characterization and System Implications of Stateful Long-Horizon WorkloadsUnderstanding and optimizing agent memory systems is crucial for improving the efficiency and scalability of long-horizon AI tasks.Jun 6, 2026LLM Agent Infra

7.0Memory is Reconstructed, Not Retrieved: Graph Memory for LLM AgentsThis approach could improve the efficiency and accuracy of LLM agents in tasks requiring long-term memory reasoning, potentially reducing computational costs.Jun 6, 2026LLM Agent Reasoning

7.5Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent ReasoningThis research addresses the critical issue of cultural misalignment in LLMs, which is essential for developing AI systems that are sensitive to diverse cultural values and improve decision-making processes.Jun 6, 2026LLM Agent Reasoning

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

6.8Do More Agents Help? Controlled and Protocol-Aligned Evaluation of LLM Agent WorkflowsUnderstanding the efficiency and effectiveness of multi-agent systems in LLM workflows can guide the development of more cost-effective and accurate AI systems.Jun 6, 2026LLM Agent Evaluation

7.5Toward Pre-Deployment Assurance for Enterprise AI Agents: Ontology-Grounded Simulation and Trust CertificationAs AI agents become integral to various industries, ensuring their compliance and safety before deployment is crucial for regulatory adherence and risk management.Jun 6, 2026Agent Security Safety

7.2Critic-Guided Heterogeneous Multi-Agent Reasoning for Reliable Mathematical Problem SolvingImproving the reliability of mathematical reasoning in LLMs can enhance their applicability in complex problem-solving tasks, reducing the need for larger models.Jun 6, 2026LLM Agent Reasoning

6.8RUBAS: Rubric-Based Reinforcement Learning for Agent SafetyAs AI agents increasingly interact with real-world tools, ensuring their safe operation is crucial for preventing unintended consequences and maintaining user trust.Jun 5, 2026LLM Agent Safety

7.5NoRA: Evaluating Grounded Reasonableness in Visual First-person Normative Action ReasoningThis research addresses a critical gap in evaluating AI's normative competence in real-world scenarios, moving beyond simple action selection to deeper reasoning.Jun 5, 2026Agent Reasoning Multimodal

6.8Simulate, Reason, Decide: Scientific Reasoning with LLMs for Simulation-Driven Decision MakingThis work is relevant for AI researchers and engineers interested in improving the transparency and reliability of decision-making systems that rely on scientific simulations.Jun 5, 2026LLM Reasoning Agent

7.5MIRAGE: Mobile Agents with Implicit Reasoning and Generative World ModelsThis work addresses the inefficiencies in mobile agent interactions, potentially streamlining applications that rely on visual and language inputs, which is crucial for real-world deployment.Jun 5, 2026Agent Reasoning Multimodal

6.8Provably Auditable and Safe LLM Agents from Human-Authored OntologiesThis work is relevant for AI engineers and researchers interested in developing reliable and auditable LLM agents for complex domains, particularly in fields like healthcare and security.Jun 5, 2026LLM Agent Security

7.2The Saturation Trap and the Subjectivity of Intervention Timing: Why Affect-Based Triggers and LLM Judges Fail to Time Interventions on Autonomous AgentsUnderstanding the limitations of intervention timing is crucial for improving the safety and effectiveness of autonomous AI systems in real-world applications.Jun 5, 2026Agent Safety Evaluation

7.5The Digital Apprentice: A Framework for Human-Directed Agentic AI DevelopmentThis framework addresses the critical challenge of ensuring accountability in AI systems while enabling their scalability, which is essential for practical applications in various fields.Jun 5, 2026Agent Alignment Architecture

6.8From Agent Traces to Trust: Evidence Tracing and Execution Provenance in LLM AgentsUnderstanding and verifying the decision-making processes of LLM agents is crucial for ensuring trust, safety, and accountability in their autonomous operations.Jun 5, 2026LLM Agent Interpretability

7.2Cosmos 3: Omnimodal World Models for Physical AIThis work could streamline the development of embodied AI systems by providing a versatile, open-source framework that integrates multiple modalities, potentially accelerating research and application in Physical AI.Jun 3, 2026Multimodal Agent Vision Language

7.2The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team SizeUnderstanding the limitations of multi-agent systems can guide researchers and engineers in designing more effective collaborative AI systems.Jun 3, 2026LLM Agent Evaluation

7.5Agentic Chain-of-Thought Steering for Efficient and Controllable LLM ReasoningThis approach addresses the inefficiencies in token usage during reasoning in large language models, providing a mechanism for better control over accuracy and efficiency, which is crucial for practical applications.Jun 3, 2026LLM Agent Reasoning

7.5Toward a Modular Architecture for Embedded AI Agent Systems at the EdgeThis work is relevant for AI engineers and researchers focused on developing efficient AI systems that operate in environments with limited computational resources, such as IoT devices.Jun 3, 2026Agent Architecture Safety

7.2Inducing Reasoning Primitives from Agent TracesThis approach could improve the efficiency and effectiveness of LLM agents by leveraging learned reasoning patterns, potentially reducing computational costs and enhancing problem-solving capabilities.Jun 3, 2026LLM Agent Reasoning

7.2Adaptive Latent Agentic ReasoningThis work is relevant for AI researchers and engineers aiming to optimize the performance of LLM agents by reducing unnecessary computational overhead while maintaining decision-making accuracy.Jun 3, 2026LLM Agent Reasoning

6.8Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile AgentsThis framework could improve the efficiency and reliability of mobile agents by reducing unnecessary interventions and optimizing resource use, which is crucial for real-time applications.Jun 3, 2026Agent Reasoning Multimodal

7.5Capability Advertisement as a Market for Lemons: A Trust Layer for Heterogeneous Agent NetworksAs LLM agents increasingly interact, establishing trust and reliability in their capabilities is crucial for effective collaboration and task delegation.Jun 3, 2026LLM Agent

7.5Towards a Science of AI Agent ReliabilityUnderstanding and improving AI agent reliability is crucial for their deployment in safety-critical applications, where failures can have serious consequences.Jun 3, 2026Agent Evaluation Safety

7.5Mechanism Design Is Not Enough: Prosocial Agents for Cooperative AIThis research highlights the limitations of existing mechanisms in AI safety and proposes a novel approach that could lead to more effective cooperative interactions among AI systems.Jun 3, 2026Agent Alignment Safety

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