Agent papers

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

423 papers found

ReviewPaperPublishedTopics

6.8Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction GameUnderstanding LLMs' capabilities in deception and reasoning is crucial for ensuring their safe deployment in high-stakes environments.Jul 31, 2026LLM Agent Reasoning

7.5Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM AgentsThis work addresses the critical challenge of deploying LLM agents in resource-constrained environments, making it relevant for practical applications in robotics and real-time decision-making systems.Jul 31, 2026LLM Agent Reasoning

7.5FirstResearch: Auditable Question Formation for LLM Scientific Discovery AgentsThis work addresses the critical issue of transparency in LLM-generated research questions, which is essential for ensuring scientific rigor and accountability in AI-assisted research.Jul 31, 2026LLM Agent Evaluation

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 31, 2026Agent Security Infra

6.8The Human Utility Factor: A Computable Welfare Metric That Reframes AI Governance as a Constrained Optimisation ProblemUnderstanding and optimizing the socioeconomic impacts of AI deployment is crucial for policymakers and researchers to ensure AI benefits society equitably.Jul 31, 2026Agent Alignment Evaluation

6.8Behavioral Controllability of Agentic Models for Information Extraction: From Fixed Workflows to Reflective AgentsUnderstanding the impact of agentic features on LLM performance can guide future developments in AI systems for complex tasks.Jul 31, 2026Other

6.8Runtime Uncertainty Monitoring for LLM-Based Multi-Agent Systems Using Bayesian NetworksUnderstanding and managing uncertainty in LLM-based systems is crucial for high-stakes applications like actuarial risk modeling, where errors can have significant consequences.Jul 30, 2026LLM Agent Interpretability

6.8Agentic AI for Scientific Reasoning in Autonomous Quantum Sensing ExperimentsThis research is relevant for AI engineers and researchers interested in the intersection of AI and quantum experiments, showcasing how autonomous agents can enhance scientific reasoning and experiment control.Jul 30, 2026LLM Agent Reasoning

6.8Toward an Organizational Science of Multi-Agent LLM Systems: Decoupling Who, How, and Which AlgorithmThis work is relevant for AI researchers and engineers interested in optimizing multi-agent systems by allowing flexible and adaptive configurations that can improve performance and efficiency.Jul 30, 2026LLM Agent Architecture

6.8Metis: Memory Foundation ModelThis work could lead to more efficient AI models with improved memory capabilities, reducing reliance on external memory modules and potentially enhancing performance in tasks requiring historical context.Jul 30, 2026LLM Architecture Agent

6.5Security and Privacy in Agentic AI: Grand Challenges and Future DirectionsUnderstanding the security and privacy implications of agentic AI is crucial for developing safe and reliable AI systems.Jul 29, 2026Security Agent Survey

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

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

6.8The Hitchhiker's Guide to Agentic AI: From Foundations to SystemsUnderstanding the full stack of agentic AI systems is crucial for developing robust, scalable, and effective autonomous agents in practical applications.Jul 28, 2026Agent LLM Alignment

7.2SQBench: A Benchmark for Evaluating Task Delivery by Language-Model Agents in Production-Oriented WorkflowsThis benchmark addresses a gap in existing evaluations by focusing on verifiable deliverables, which is crucial for real-world applications of language models in production settings.Jul 28, 2026Benchmark Evaluation LLM

8.2DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMsThis research demonstrates that structured workflows can enhance diagnostic reasoning in medical AI, potentially improving clinical outcomes and reducing costs.Jul 28, 2026LLM Agent Reasoning

6.8Spatial Reasoning in LLM Game Agents: Impact of Causal Context and Multi-Step PlanningUnderstanding and improving spatial reasoning in LLM game agents can enhance their performance in complex tasks, which is crucial for developing more advanced AI systems.Jul 28, 2026LLM Agent Reasoning

6.8When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social DilemmasUnderstanding how LLMs navigate ethical dilemmas is crucial for their safe deployment in real-world scenarios where moral and profit incentives may conflict.Jul 27, 2026LLM Agent Alignment

7.2LeAct: Learning to Reason from Expert ActionsThis approach provides a novel way to extract reasoning from expert systems, potentially enhancing the capabilities of AI models in complex domains.Jul 27, 2026Reasoning Agent Robotics

6.5Safeguards for Speech2Speech LLM-Assistants: A Case Study in Automotive ApplicationsUnderstanding the limitations of S2S guardrails is crucial for developing reliable and safe conversational AI systems in vehicles.Jul 24, 2026Safety Agent LLM

6.8Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of MindUnderstanding and improving AI's ability to model and manipulate beliefs is crucial for developing robust systems capable of safe interactions in adversarial settings.Jul 24, 2026LLM Agent Reasoning

6.5Auditing Provenance Sensitivity in LLM Agent Action SelectionUnderstanding how LLM agents are influenced by trusted and untrusted evidence is crucial for improving their decision-making reliability and security.Jul 24, 2026LLM Agent Evaluation

7.2SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent SafetyAs LLMs evolve into autonomous agents, ensuring their safe operation in real-world environments is crucial to prevent misuse and maintain user trust.Jul 24, 2026LLM Agent Security

7.5LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State ProprioceptionThis work addresses a critical limitation in long-horizon tool agents, potentially improving their effectiveness in real-world applications where context management is crucial.Jul 24, 2026LLM Agent Evaluation

7.0OpenSkillRisk: Benchmarking Agent Safety When Using Real-World Risky Third-Party SkillsUnderstanding and improving agent safety when using third-party skills is crucial for deploying reliable AI systems in real-world applications.Jul 24, 2026LLM Agent Safety

6.8JANUS: Foreseeing Latent Risk for Long-Horizon Agent SafetyImproving agent safety by predicting and preventing risks can significantly enhance the reliability and trustworthiness of AI systems in real-world applications.Jul 23, 2026Agent Safety

8.2Rewriting the Response Path: Silent Tampering and Provider-Signed Defense in BYOK LLM AgentsUnderstanding and mitigating response-path attacks is crucial for ensuring the reliability and security of LLM applications, especially in sensitive contexts.Jul 23, 2026LLM Agent Security

7.2NEXUS: Structured Runtime Safety for Tool-Using LLM AgentsAs LLM agents increasingly perform high-impact actions, ensuring their safe operation is crucial for preventing unintended consequences in real-world applications.Jul 23, 2026LLM Agent Safety

6.5The Ethics of Autonomous AI Agents for Offensive SecurityUnderstanding the ethical implications of autonomous AI in security is crucial for developing responsible AI technologies and policies.Jul 23, 2026LLM Agent Security

6.8Will the Agent Recuse, and Will It Stop? Measuring LLM-Agent Compliance with In-Band Governance Signals at the Access Door and Mid-FlightUnderstanding and improving LLM agent compliance with governance signals is crucial for safe and controlled deployment in real-world applications.Jul 23, 2026LLM Agent Security

7.2Operational Hallucination and Safety Drift in AI AgentsUnderstanding and mitigating reliability risks in AI agents is crucial for safe deployment in real-world applications, especially in high-stakes scenarios.Jul 22, 2026LLM Agent Safety

6.8Engineering Trustworthy Agentic AI for Critical SystemsUnderstanding and ensuring the trustworthiness of agentic AI is crucial for their safe deployment in critical systems where failures can have significant consequences.Jul 22, 2026Agent Safety Security

7.5SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied AgentsAs AI systems increasingly operate in physical environments, ensuring their safety through formal methods is crucial for real-world applications and public trust.Jul 22, 2026Safety Evaluation Agent

7.5LinguistAgent Technical Report: A Reflective Multi-Model Platform for Automated Linguistic AnnotationThis research addresses a critical bottleneck in humanities and social sciences by enhancing the efficiency of linguistic annotation, which is essential for various research applications.Jul 22, 2026LLM Agent Evaluation

7.5When JSON Is Not Enough: Semantic Reliability of Schema-Constrained LLM Ordering AgentsUnderstanding the limitations of schema validation is crucial for developers relying on LLMs for safe and accurate transaction processing.Jul 22, 2026LLM Agent Evaluation

6.8Agents in the Wild: Where Research Meets DeploymentUnderstanding the deployment challenges and solutions for agentic systems is crucial for AI engineers and researchers aiming to implement these systems in real-world applications.Jul 22, 2026LLM Agent Reasoning

6.5Alignment of a Total Automation EconomyUnderstanding the economic structure of a total automation economy is crucial for developing effective AI systems that align with human values and market dynamics.Jul 22, 2026Alignment Agent

6.8Towards Agentic Agent-based Models: Feasibility, Performance, and Statistical Model CheckingUnderstanding the integration of LLMs into ABMs could enhance the modeling of complex systems by providing more nuanced decision-making capabilities, potentially leading to more accurate simulations.Jul 21, 2026LLM Agent Evaluation

7.5AgentBrew: Lifelong Knowledge Brewing from Strong Teachers to Weak LLM AgentsThis approach could significantly enhance the performance of LLM agents in practical applications by leveraging existing expertise without the need for extensive retraining.Jul 21, 2026LLM Agent Coding

7.2Agentic ERP: Multi-Agent Large Language Model Architecture for Autonomous Enterprise Resource PlanningThis work is relevant for AI researchers and engineers interested in applying LLMs to automate complex enterprise systems, potentially reducing human workload and improving operational efficiency.Jul 21, 2026LLM Agent Architecture

6.8LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and ApplicationsThis work is relevant for AI researchers and engineers interested in applying LLMs to technical domains like smart grids, offering a structured approach to ensure reliable and accurate outputs.Jul 21, 2026LLM Agent Evaluation

7.0Reward-Driven LLM Agent Workflows: Synthesizing POMDP Routing and Self-Correction for Autonomous Decision-MakingThis research could enhance the autonomy and efficiency of AI agents in complex environments, which is crucial for developing more capable and reliable AI systems.Jul 21, 2026LLM Agent Reasoning

7.2AoA: Theorem Proving Agent over Abstract Syntax Tree of Redesigned LanguageThis approach could significantly reduce the computational and financial costs associated with theorem proving, making it more scalable and accessible for program verification and formalized mathematics.Jul 21, 2026LLM Agent Reasoning

6.8Specifying the Delegated-Autonomy Boundary: Requirements Engineering for Agentic AIUnderstanding and specifying the delegated-autonomy boundary is crucial for developing safe and effective AI systems that operate with varying levels of autonomy.Jul 21, 2026Agent Safety

7.8RAIL Guard: Closing the Evaluation-to-Remediation Gap in Responsible AI for LLM AgentsThis research addresses critical gaps in responsible AI by providing a systematic method to enhance the safety and utility of LLM outputs, which is essential for organizations deploying these technologies.Jul 21, 2026LLM Agent Evaluation

7.5OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent CollaborationThis work addresses a gap in the systematic design and optimization of LLM-based multi-agent systems, which is crucial for enhancing their performance in complex tasks.Jul 21, 2026LLM Agent Reasoning

6.8SeerGuard: A Safety Framework for Mobile GUI Agents via World Model PredictionAs mobile GUI agents become more prevalent, ensuring their safe operation is crucial to prevent potentially irreversible errors.Jul 20, 2026Agent Safety Security

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

6.8Scalable LLM Agent Tool Access in the CloudThis work is relevant for AI engineers and researchers focusing on improving the efficiency and scalability of LLM agents interacting with external tools in cloud environments.Jul 20, 2026LLM Agent Infra

6.8Provable Coordination for LLM Agents via Message Sequence ChartsThis work provides a structured approach to managing coordination in LLM-based multi-agent systems, potentially reducing errors like deadlocks and improving reliability.Jul 18, 2026LLM Agent Reasoning