{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/ai-agent/papers/2","list_of":"/task/ai-agent","task":"AI Agent","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":4,"rows_per_page":100,"rows":[101,200],"of":391,"counts":{"archive_papers_tagged":391,"with_a_code_link":111,"where_syntology_ran_a_sample":36,"not_listed_spam_title":0,"listed":391,"listed_where_code_ran":36,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":28,"every_run_a_failure_of_syntologys_instrument":8,"listed_with_a_run_with_no_instrument_failure":28,"listed_every_run_a_failure_of_syntologys_instrument":8,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/ai-agent","prev":"/task/ai-agent","next":"/task/ai-agent/papers/3","papers":[{"url":"/paper/look-wide-and-interpret-twice-improving","slug":"look-wide-and-interpret-twice-improving","title":"Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks","date":"2021-06-01","arxiv_id":"2106.00596","repositories_listed":1,"syntology":null},{"url":"/paper/ensemble-of-mrr-and-ndcg-models-for-visual","slug":"ensemble-of-mrr-and-ndcg-models-for-visual","title":"Ensemble of MRR and NDCG models for Visual Dialog","date":"2021-04-15","arxiv_id":"2104.07511","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ensemble-of-mrr-and-ndcg-models-for-visual#ran","syntology_url":"https://syntology.ai/paper/2104.07511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07511"}},"official":{"repos":["idansc/mrr-ndcg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tstarbot-x-an-open-sourced-and-comprehensive","slug":"tstarbot-x-an-open-sourced-and-comprehensive","title":"TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game","date":"2020-11-27","arxiv_id":"2011.13729","repositories_listed":1,"syntology":null},{"url":"/paper/watch-and-help-a-challenge-for-social-1","slug":"watch-and-help-a-challenge-for-social-1","title":"Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration","date":"2020-10-19","arxiv_id":"2010.09890","repositories_listed":1,"syntology":null},{"url":"/paper/finding-game-levels-with-the-right-difficulty","slug":"finding-game-levels-with-the-right-difficulty","title":"Finding Game Levels with the Right Difficulty in a Few Trials through Intelligent Trial-and-Error","date":"2020-05-15","arxiv_id":"2005.07677","repositories_listed":1,"syntology":null},{"url":"/paper/clai-a-platform-for-ai-skills-on-the-command","slug":"clai-a-platform-for-ai-skills-on-the-command","title":"Project CLAI: Instrumenting the Command Line as a New Environment for AI Agents","date":"2020-01-31","arxiv_id":"2002.00762","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clai-a-platform-for-ai-skills-on-the-command#ran","syntology_url":"https://syntology.ai/paper/2002.00762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.00762"}},"official":{"repos":["ibm/clai"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/scail-classifier-weights-scaling-for-class","slug":"scail-classifier-weights-scaling-for-class","title":"ScaIL: Classifier Weights Scaling for Class Incremental Learning","date":"2020-01-16","arxiv_id":"2001.05755","repositories_listed":1,"syntology":null},{"url":"/paper/dmrm-a-dual-channel-multi-hop-reasoning-model","slug":"dmrm-a-dual-channel-multi-hop-reasoning-model","title":"DMRM: A Dual-channel Multi-hop Reasoning Model for Visual Dialog","date":"2019-12-18","arxiv_id":"1912.08360","repositories_listed":1,"syntology":null},{"url":"/paper/knowledgeable-storyteller-a-commonsense","slug":"knowledgeable-storyteller-a-commonsense","title":"Knowledgeable Storyteller: A Commonsense-Driven Generative Model for Visual Storytelling","date":"2019-05-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/shallow-decision-making-analysis-in-general","slug":"shallow-decision-making-analysis-in-general","title":"Shallow decision-making analysis in General Video Game Playing","date":"2018-06-04","arxiv_id":"1806.01151","repositories_listed":1,"syntology":null},{"url":"/paper/octopus-a-framework-for-cost-quality-time","slug":"octopus-a-framework-for-cost-quality-time","title":"Octopus: A Framework for Cost-Quality-Time Optimization in Crowdsourcing","date":"2017-02-12","arxiv_id":"1702.03488","repositories_listed":1,"syntology":null},{"url":null,"slug":"token-compression-meets-compact-vision","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","date":"2025-07-13","arxiv_id":"2507.09702","repositories_listed":0,"syntology":null},{"url":null,"slug":"openagentsafety-a-comprehensive-framework-for","title":"OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety","date":"2025-07-08","arxiv_id":"2507.06134","repositories_listed":0,"syntology":null},{"url":null,"slug":"stella-self-evolving-llm-agent-for-biomedical","title":"STELLA: Self-Evolving LLM Agent for Biomedical Research","date":"2025-07-01","arxiv_id":"2507.02004","repositories_listed":0,"syntology":null},{"url":null,"slug":"prover-agent-an-agent-based-framework-for","title":"Prover Agent: An Agent-based Framework for Formal Mathematical Proofs","date":"2025-06-24","arxiv_id":"2506.19923","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-agents-as-judge-automated-assessment-of","title":"AI Agents-as-Judge: Automated Assessment of Accuracy, Consistency, Completeness and Clarity for Enterprise Documents","date":"2025-06-23","arxiv_id":"2506.22485","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-big-five-personality-and-ai","title":"Exploring Big Five Personality and AI Capability Effects in LLM-Simulated Negotiation Dialogues","date":"2025-06-19","arxiv_id":"2506.15928","repositories_listed":0,"syntology":null},{"url":null,"slug":"xbench-tracking-agents-productivity-scaling","title":"xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations","date":"2025-06-16","arxiv_id":"2506.13651","repositories_listed":0,"syntology":null},{"url":null,"slug":"indoorworld-integrating-physical-task-solving","title":"IndoorWorld: Integrating Physical Task Solving and Social Simulation in A Heterogeneous Multi-Agent Environment","date":"2025-06-14","arxiv_id":"2506.12331","repositories_listed":0,"syntology":null},{"url":null,"slug":"adagent-llm-agent-for-alzheimer-s-disease","title":"ADAgent: LLM Agent for Alzheimer's Disease Analysis with Collaborative Coordinator","date":"2025-06-11","arxiv_id":"2506.11150","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-06576","title":"Future of Work with AI Agents: Auditing Automation and Augmentation Potential across the U.S. Workforce","date":"2025-06-06","arxiv_id":"2506.06576","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolutionary-perspectives-on-the-evaluation","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","date":"2025-06-06","arxiv_id":"2506.11102","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-agent-behavioral-science","title":"AI Agent Behavioral Science","date":"2025-06-04","arxiv_id":"2506.06366","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-agents-for-conversational-patient-triage","title":"AI Agents for Conversational Patient Triage: Preliminary Simulation-Based Evaluation with Real-World EHR Data","date":"2025-06-04","arxiv_id":"2506.04032","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-cost-of-dynamic-reasoning-demystifying-ai","title":"The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective","date":"2025-06-04","arxiv_id":"2506.04301","repositories_listed":0,"syntology":null},{"url":null,"slug":"atag-ai-agent-application-threat-assessment","title":"ATAG: AI-Agent Application Threat Assessment with Attack Graphs","date":"2025-06-03","arxiv_id":"2506.02859","repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-algorithmic-delegates-the-role-of","title":"Designing Algorithmic Delegates: The Role of Indistinguishability in Human-AI Handoff","date":"2025-06-03","arxiv_id":"2506.03102","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-language-models-are-the-future-of","title":"Small Language Models are the Future of Agentic AI","date":"2025-06-02","arxiv_id":"2506.02153","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-ai-master-econometrics-evidence-from","title":"Can AI Master Econometrics? Evidence from Econometrics AI Agent on Expert-Level Tasks","date":"2025-06-01","arxiv_id":"2506.00856","repositories_listed":0,"syntology":null},{"url":null,"slug":"hada-human-ai-agent-decision-alignment","title":"HADA: Human-AI Agent Decision Alignment Architecture","date":"2025-06-01","arxiv_id":"2506.04253","repositories_listed":0,"syntology":null},{"url":null,"slug":"dyna-think-synergizing-reasoning-acting-and","title":"Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents","date":"2025-05-31","arxiv_id":"2506.00320","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-ai-powered-knowledge-hub-for-potato","title":"An AI-powered Knowledge Hub for Potato Functional Genomics","date":"2025-05-30","arxiv_id":"2506.00082","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-symbiotic-ai-and-non-ai-agent-based","title":"Scalable, Symbiotic, AI and Non-AI Agent Based Parallel Discrete Event Simulations","date":"2025-05-28","arxiv_id":"2505.23846","repositories_listed":0,"syntology":null},{"url":null,"slug":"chemhas-hierarchical-agent-stacking-for","title":"ChemHAS: Hierarchical Agent Stacking for Enhancing Chemistry Tools","date":"2025-05-27","arxiv_id":"2505.21569","repositories_listed":0,"syntology":null},{"url":null,"slug":"ggbond-growing-graph-based-ai-agent-society","title":"GGBond: Growing Graph-Based AI-Agent Society for Socially-Aware Recommender Simulation","date":"2025-05-27","arxiv_id":"2505.21154","repositories_listed":0,"syntology":null},{"url":null,"slug":"ten-principles-of-ai-agent-economics","title":"Ten Principles of AI Agent Economics","date":"2025-05-26","arxiv_id":"2505.20273","repositories_listed":0,"syntology":null},{"url":null,"slug":"get-experience-from-practice-llm-agents-with","title":"Get Experience from Practice: LLM Agents with Record & Replay","date":"2025-05-23","arxiv_id":"2505.17716","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-systems-for-misinformation","title":"Multi-agent Systems for Misinformation Lifecycle : Detection, Correction And Source Identification","date":"2025-05-23","arxiv_id":"2505.17511","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-powered-ai-agent-systems-and-their","title":"LLM-Powered AI Agent Systems and Their Applications in Industry","date":"2025-05-22","arxiv_id":"2505.16120","repositories_listed":0,"syntology":null},{"url":null,"slug":"bountybench-dollar-impact-of-ai-agent","title":"BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems","date":"2025-05-21","arxiv_id":"2505.15216","repositories_listed":0,"syntology":null},{"url":null,"slug":"confidence-regulated-generative-diffusion","title":"Confidence-Regulated Generative Diffusion Models for Reliable AI Agent Migration in Vehicular Metaverses","date":"2025-05-19","arxiv_id":"2505.12710","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-a-reinforcement-learning-agent","title":"When a Reinforcement Learning Agent Encounters Unknown Unknowns","date":"2025-05-19","arxiv_id":"2505.13188","repositories_listed":0,"syntology":null},{"url":null,"slug":"taiji-mcp-based-multi-modal-data-analytics-on","title":"TAIJI: MCP-based Multi-Modal Data Analytics on Data Lakes","date":"2025-05-16","arxiv_id":"2505.11270","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-agents-vs-agentic-ai-a-conceptual-taxonomy","title":"AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges","date":"2025-05-15","arxiv_id":"2505.10468","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-user-centered-interactive-medical","title":"Towards user-centered interactive medical image segmentation in VR with an assistive AI agent","date":"2025-05-12","arxiv_id":"2505.07214","repositories_listed":0,"syntology":null},{"url":null,"slug":"bi-lstm-based-multi-agent-drl-with","title":"Bi-LSTM based Multi-Agent DRL with Computation-aware Pruning for Agent Twins Migration in Vehicular Embodied AI Networks","date":"2025-05-09","arxiv_id":"2505.06378","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-mind-to-machine-the-rise-of-manus-ai-as","title":"From Mind to Machine: The Rise of Manus AI as a Fully Autonomous Digital Agent","date":"2025-05-04","arxiv_id":"2505.02024","repositories_listed":0,"syntology":null},{"url":null,"slug":"irl-dittos-embodied-multimodal-ai-agent","title":"IRL Dittos: Embodied Multimodal AI Agent Interactions in Open Spaces","date":"2025-04-30","arxiv_id":"2504.21347","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-federation-for-mixtures-of-proprietary","title":"Online Federation For Mixtures of Proprietary Agents with Black-Box Encoders","date":"2025-04-30","arxiv_id":"2505.00216","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-ai-agents-design-and-implement-drug","title":"Can AI Agents Design and Implement Drug Discovery Pipelines?","date":"2025-04-28","arxiv_id":"2504.19912","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-multi-agent-systems-through-model","title":"Advancing Multi-Agent Systems Through Model Context Protocol: Architecture, Implementation, and Applications","date":"2025-04-26","arxiv_id":"2504.21030","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-ai-agent-protocols","title":"A Survey of AI Agent Protocols","date":"2025-04-23","arxiv_id":"2504.16736","repositories_listed":0,"syntology":null},{"url":null,"slug":"trust-but-verify","title":"Trust, but verify","date":"2025-04-18","arxiv_id":"2504.13443","repositories_listed":0,"syntology":null},{"url":null,"slug":"tinker-tales-interactive-storytelling","title":"Tinker Tales: Interactive Storytelling Framework for Early Childhood Narrative Development and AI Literacy","date":"2025-04-17","arxiv_id":"2504.13969","repositories_listed":0,"syntology":null},{"url":null,"slug":"loka-protocol-a-decentralized-framework-for","title":"LOKA Protocol: A Decentralized Framework for Trustworthy and Ethical AI Agent Ecosystems","date":"2025-04-15","arxiv_id":"2504.10915","repositories_listed":0,"syntology":null},{"url":null,"slug":"ctrl-z-controlling-ai-agents-via-resampling","title":"Ctrl-Z: Controlling AI Agents via Resampling","date":"2025-04-14","arxiv_id":"2504.10374","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-based-ai-agent-for-sizing-of-analog-and","title":"LLM-based AI Agent for Sizing of Analog and Mixed Signal Circuit","date":"2025-04-14","arxiv_id":"2504.11497","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-commit-helping-users-update-intent","title":"Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale","date":"2025-04-12","arxiv_id":"2504.09283","repositories_listed":0,"syntology":null},{"url":null,"slug":"marmot-multi-agent-reasoning-for-multi-object","title":"Marmot: Multi-Agent Reasoning for Multi-Object Self-Correcting in Improving Image-Text Alignment","date":"2025-04-10","arxiv_id":"2504.20054","repositories_listed":0,"syntology":null},{"url":null,"slug":"throughput-optimal-scheduling-algorithms-for","title":"Throughput-Optimal Scheduling Algorithms for LLM Inference and AI Agents","date":"2025-04-10","arxiv_id":"2504.07347","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-in-a-vat-fundamental-limits-of-efficient","title":"AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability","date":"2025-04-06","arxiv_id":"2504.04608","repositories_listed":0,"syntology":null},{"url":"/paper/multi-mission-tool-bench-assessing-the","slug":"multi-mission-tool-bench-assessing-the","title":"Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions","date":"2025-04-03","arxiv_id":"2504.02623","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-agent-reasoning-in-image-schemas-a","title":"Grounding Agent Reasoning in Image Schemas: A Neurosymbolic Approach to Embodied Cognition","date":"2025-03-31","arxiv_id":"2503.24110","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-aversion-do-ai-agents-judge-identity","title":"Human aversion? Do AI Agents Judge Identity More Harshly Than Performance","date":"2025-03-31","arxiv_id":"2504.13871","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-person-one-bot","title":"One Person, One Bot","date":"2025-03-31","arxiv_id":"2504.01039","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-theoretical-framework-for-prompt","title":"A Theoretical Framework for Prompt Engineering: Approximating Smooth Functions with Transformer Prompts","date":"2025-03-26","arxiv_id":"2503.20561","repositories_listed":0,"syntology":null},{"url":null,"slug":"deterministic-ai-agent-personality-expression","title":"Deterministic AI Agent Personality Expression through Standard Psychological Diagnostics","date":"2025-03-21","arxiv_id":"2503.17085","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-agents-in-cryptoland-practical-attacks-and","title":"Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents","date":"2025-03-20","arxiv_id":"2503.16248","repositories_listed":0,"syntology":null},{"url":null,"slug":"experimental-exploration-investigating","title":"When Trust Collides: Decoding Human-LLM Cooperation Dynamics through the Prisoner's Dilemma","date":"2025-03-10","arxiv_id":"2503.07320","repositories_listed":0,"syntology":null},{"url":null,"slug":"higher-order-belief-in-incomplete-information","title":"Higher-Order Belief in Incomplete Information MAIDs","date":"2025-03-08","arxiv_id":"2503.06323","repositories_listed":0,"syntology":null},{"url":null,"slug":"which-books-do-i-like","title":"Which books do I like?","date":"2025-03-05","arxiv_id":"2503.03300","repositories_listed":0,"syntology":null},{"url":null,"slug":"realjam-real-time-human-ai-music-jamming-with","title":"ReaLJam: Real-Time Human-AI Music Jamming with Reinforcement Learning-Tuned Transformers","date":"2025-02-28","arxiv_id":"2502.21267","repositories_listed":0,"syntology":null},{"url":null,"slug":"telephone-surveys-meet-conversational-ai","title":"Telephone Surveys Meet Conversational AI: Evaluating a LLM-Based Telephone Survey System at Scale","date":"2025-02-27","arxiv_id":"2502.20140","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-are-web-ai-agents-more-vulnerable-than","title":"Why Are Web AI Agents More Vulnerable Than Standalone LLMs? A Security Analysis","date":"2025-02-27","arxiv_id":"2502.20383","repositories_listed":0,"syntology":null},{"url":null,"slug":"graphy-our-data-towards-end-to-end-modeling","title":"Graphy'our Data: Towards End-to-End Modeling, Exploring and Generating Report from Raw Data","date":"2025-02-24","arxiv_id":"2502.16868","repositories_listed":0,"syntology":null},{"url":null,"slug":"um-fhs-at-trec-2024-plaba-exploration-of-fine","title":"UM_FHS at TREC 2024 PLABA: Exploration of Fine-tuning and AI agent approach for plain language adaptations of biomedical text","date":"2025-02-19","arxiv_id":"2502.14144","repositories_listed":0,"syntology":null},{"url":null,"slug":"mudoc-an-interactive-multimodal-document","title":"MuDoC: An Interactive Multimodal Document-grounded Conversational AI System","date":"2025-02-14","arxiv_id":"2502.09843","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-ai-off-switch-problem-as-a-signalling","title":"The AI off-switch problem as a signalling game: bounded rationality and incomparability","date":"2025-02-10","arxiv_id":"2502.06403","repositories_listed":0,"syntology":null},{"url":null,"slug":"barriers-and-pathways-to-human-ai-alignment-a","title":"Barriers and Pathways to Human-AI Alignment: A Game-Theoretic Approach","date":"2025-02-09","arxiv_id":"2502.05934","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-application-of-matec-multi-ai-agent-team","title":"The Application of MATEC (Multi-AI Agent Team Care) Framework in Sepsis Care","date":"2025-02-09","arxiv_id":"2503.16433","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-active-human-involvement-1","title":"Learning from Active Human Involvement through Proxy Value Propagation","date":"2025-02-05","arxiv_id":"2502.03369","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-ai-agent-index","title":"The AI Agent Index","date":"2025-02-03","arxiv_id":"2502.01635","repositories_listed":0,"syntology":null},{"url":null,"slug":"toolfactory-automating-tool-generation-by","title":"ToolFactory: Automating Tool Generation by Leveraging LLM to Understand REST API Documentations","date":"2025-01-28","arxiv_id":"2501.16945","repositories_listed":0,"syntology":null},{"url":null,"slug":"caprag-a-large-language-model-solution-for","title":"CAPRAG: A Large Language Model Solution for Customer Service and Automatic Reporting using Vector and Graph Retrieval-Augmented Generation","date":"2025-01-23","arxiv_id":"2501.13993","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-agentic-workflows-and-enterprise-apis","title":"AI Agentic workflows and Enterprise APIs: Adapting API architectures for the age of AI agents","date":"2025-01-22","arxiv_id":"2502.17443","repositories_listed":0,"syntology":null},{"url":null,"slug":"episodic-memory-in-ai-agents-poses-risks-that","title":"Episodic memory in AI agents poses risks that should be studied and mitigated","date":"2025-01-20","arxiv_id":"2501.11739","repositories_listed":0,"syntology":null},{"url":null,"slug":"authenticated-delegation-and-authorized-ai","title":"Authenticated Delegation and Authorized AI Agents","date":"2025-01-16","arxiv_id":"2501.09674","repositories_listed":0,"syntology":null},{"url":null,"slug":"sop-agent-empower-general-purpose-ai-agent","title":"SOP-Agent: Empower General Purpose AI Agent with Domain-Specific SOPs","date":"2025-01-16","arxiv_id":"2501.09316","repositories_listed":0,"syntology":null},{"url":null,"slug":"yeti-yet-to-intervene-proactive-interventions","title":"YETI (YET to Intervene) Proactive Interventions by Multimodal AI Agents in Augmented Reality Tasks","date":"2025-01-16","arxiv_id":"2501.09355","repositories_listed":0,"syntology":null},{"url":null,"slug":"personality-modeling-for-persuasion-of","title":"Personality Modeling for Persuasion of Misinformation using AI Agent","date":"2025-01-15","arxiv_id":"2501.08985","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-big-five-personality-traits-on","title":"The Impact of Big Five Personality Traits on AI Agent Decision-Making in Public Spaces: A Social Simulation Study","date":"2025-01-15","arxiv_id":"2503.15497","repositories_listed":0,"syntology":null},{"url":null,"slug":"strategy-masking-a-method-for-guardrails-in","title":"Strategy Masking: A Method for Guardrails in Value-based Reinforcement Learning Agents","date":"2025-01-09","arxiv_id":"2501.05501","repositories_listed":0,"syntology":null},{"url":null,"slug":"finsphere-a-conversational-stock-analysis","title":"FinSphere: A Conversational Stock Analysis Agent Equipped with Quantitative Tools based on Real-Time Database","date":"2025-01-08","arxiv_id":"2501.12399","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-workplace-productivity-and-well","title":"Enhancing Workplace Productivity and Well-being Using AI Agent","date":"2025-01-04","arxiv_id":"2501.02368","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-new-hdls-with-agents","title":"Enabling New HDLs with Agents","date":"2024-12-31","arxiv_id":"2501.00642","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-agent-for-education-von-neumann-multi","title":"AI Agent for Education: von Neumann Multi-Agent System Framework","date":"2024-12-30","arxiv_id":"2501.00083","repositories_listed":0,"syntology":null},{"url":null,"slug":"will-you-donate-money-to-a-chatbot-the-effect","title":"Will you donate money to a chatbot? The effect of chatbot anthropomorphic features and persuasion strategies on willingness to donate","date":"2024-12-28","arxiv_id":"2412.19976","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-ai-agent-system-for-autonomous","title":"A Multi-AI Agent System for Autonomous Optimization of Agentic AI Solutions via Iterative Refinement and LLM-Driven Feedback Loops","date":"2024-12-22","arxiv_id":"2412.17149","repositories_listed":0,"syntology":null},{"url":null,"slug":"modular-conversational-agents-for-surveys-and","title":"Modular Conversational Agents for Surveys and Interviews","date":"2024-12-22","arxiv_id":"2412.17049","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-quantification-in-continual-open","title":"Uncertainty Quantification in Continual Open-World Learning","date":"2024-12-21","arxiv_id":"2412.16409","repositories_listed":0,"syntology":null}],"record_sha256":"5c2b6abf8597e8d4acf384cfacce1cc77f887484bbd4451e777bcfa48ec7e02b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}