Call

Ask about this topic

Momentum

13 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 38

All topics
CardsList

  1. Sapien: A Stateful Policy Engine for Autonomous AI Agents

    Sep 30, 2026Corinn Tiffany, Wen Zhang, Eugene Bagdasarian +1Artificial Intelligence AgentsArtificial Intelligence Safety

    Google · University of Massachusetts Amherst

  2. Unapologetically Distributed: A Call for Decentralized Document Analysis

    Sep 30, 2026Adrià Molina, Oriol Ramos Terrades, Josep LladósFederated LearningOut-Of-Distribution

    Centre de Visió per Computador Universitat Autònoma de Barcelona Bellaterra, Catalonia · Computer Science Department Universitat Autònoma de Barcelona, Bellaterra, Catalonia

  3. ActionGuard: Tool Call Authorization under Poisoned Skills

    Sep 30, 2026Jihun Han, Yejin Jang, Byung Il Kwak +1Tool InvocationAuthorization

    Korea University Republic of Korea

  4. Bad: Taming the Bioacoustic Data Deluge with a Bat Activity Detector

    Sep 29, 2026Stefano Ciapponi, Santiago Martinez Balvanera, Andrea Cesaretti +2Passive Acoustic MonitoringCortex

    Fondazione Bruno Kessler · University of Trento · University College London

  5. When Valid Tool Calls Change Meaning: Formation-Consistent Dispatch for LLM Agents

    Sep 28, 2026Geonwoo Kim, Brent ByungHoon KangAgentic DeploymentsCall

    Korea Advanced Institute of Science and Technology

  6. Toolcompass: Guiding Tool Trialing, Not Suppressing It

    Sep 22, 2026Junlin Fang, Chong Zhang, Do Nguyen-Thanh +3Political Compass TestCall

    College of Computing and Data Science, Nanyang Technological University · Zhejiang University · Australian Artificial Intelligence Institute, University of Technology Sydney +1

  7. Narrowband Voice Communication Using Streaming Neural Compression

    Sep 21, 2026Dahong Luo, Anannya Trehan, Aritrik Ghosh +1Neural Speech CodecsNeural Audio Codecs

    University of Maryland, College Park

  8. A frontend-backend architecture for tool calls in full-duplex speech models

    Sep 16, 2026Ke Hu, Slyne Deng, Chen Chen +10Full-Duplex Speech ModelsCall

    NVIDIA, USA

  9. Ask the Tool, Don't Guess: Agent Tool Calls Hold Their Progress, and the Serving System Should Read It

    Sep 16, 2026Yipeng Liu, Yingqiang Zhang, Feifei Li +1CallKey-Value Cache

    Tsinghua University, China · Alibaba Cloud Computing, China · Zhejiang University, China

  10. VLA-ULAP: Interleaving Cloud VLA Calls with Ultra-Lightweight Local Action Prediction at the Edge

    Sep 16, 2026Deyu Cao, Ryuji Oi, Kosuke Matsushima +4Action PredictionRemote

    The University of Tokyo · Institute of Science Tokyo

  11. When to Call an LLM: A Confidence-Gated Hybrid for Cost-Effective Emotion Recognition in Conversational AI

    Sep 16, 2026Sai Babu Udayagiri, Arjun Chouhan, Ravisekhar Kanagala +1Conversational Artificial IntelligenceEmotion Recognition

    Five9

  12. When Tool Calls Succeed but Workflows Fail: Anomalies at the Agent-Tool Boundary

    Sep 14, 2026Artem Trofimov, Boris NovikovTool InvocationAgentic Workflow Design

    AVIV Group · Independent Researcher

  13. The Machines Are Calling: Measuring Automated and Synthetic Voices in Unwanted Inbound Calls

    Sep 10, 2026Xingyu Shen, Tommy Duong, Muduo Xu +8DialCall

    Scam AI (Reality Inc.)

  14. Interface-Induced Trajectory Censoring

    Sep 3, 2026Wenbo WangCall

    City University of Hong Kong

  15. Making Every Tool Call Count: Necessary Tool-Evidence Path Rewards for Agentic Vision-Language Models

    Sep 3, 2026Xingming Long, Yu Liu, Zhiwei Yang +7Recent Vision-Language ModelsProcess-Level Supervision

    MiLM Plus, Xiaomi Inc.3 · Institute of Information Engineering, Chinese Academy of Sciences1 · Department of Machine Learning, Carnegie Mellon University2

  16. Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach

    Aug 3, 2026Mohamed Chahine GhanemCollusionSteganography

    Keele University, Newcastle-Under-Lyme, U.K.

  17. CallScreenBench: Benchmarking On-Device Models as Phone Secretaries

    Aug 2, 2026Simiao RenDialCall

  18. Verified Tool Calls Improve LLM Agent Reliability Under Non-Atomic Failures

    Jul 31, 2026Isham Kalappurackal Mansoor, Abhishek Phadke, Pratip RanaLarge Language Model AgentsCall

    Department of Computer Science Old Dominion University Norfolk, VA 23529 · School of Engineering and Computing Christopher Newport University Newport News, VA 23606

  19. Two Calls Beat Five Agents: Evaluating Multi-Agent Pipelines Against Self-Refinement for Local Language Models

    Jul 29, 2026Ashish Prajapati, Om MohiteMulti-Agent Large Language Model SystemsLanguage Modeling

    Independent Researcher Mumbai, India

  20. Speculate While You Reason: Teaching Agents to Predict Their Next Tool Call via Joint Agent-Speculator RL

    Jul 28, 2026Jiabao Ji, Yujian Liu, Li An +4Large Language Model AgentsSelf-Speculative

    University of California, Santa Barbara · Linkedin Inc

  21. ChainWatch: A Kill Chain-Aligned Sequential Detection Framework for Multi-Step Attacks in MCP-Based AI Agent Systems

    Jul 20, 2026Om Narayan, Rashmi Jyoti, Ramkinker SinghThreat DetectionModel Context Protocol

    Computer Science New York University New York, USA · Cybersecurity University of Maryland, College Park MD, USA · Carnegie Mellon University Pittsburgh, USA

  22. ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs

    Jul 15, 2026Aryan Keluskar, Amrita Bhattacharjee, Huan LiuLarge Language Model SafetyAgentic Deployments

    School of Computing & AI, Arizona State University, Tempe, AZ, USA.

  23. Constraint Tax in Open-Weight LLMs: An Empirical Study of Tool Calling Suppression Under Structured Output Constraints

    Jun 24, 2026Fangzheng Li, Aimin Zhang, Chen LvTool InvocationCall

    1Focus AI Center, Focus Technology Co., Ltd. · 2Nanjing University of Science and Technology

  24. Ghost Tool Calls: Issue-Time Privacy for Speculative Agent Tools

    Jun 1, 2026Bardia Mohammadi, Lars Klein, Akhil Arora +1Tool InvocationCall

    Max Planck Institute for Software Systems · EPFL · Aarhus University

  25. Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains

    Jun 1, 2026Garvin Guo, Donglei Yu, Yu Chen +6Multimodal AgentsCall

    University of Chinese Academy of Sciences · Tongyi Lab, Alibaba Group · Amap, Alibaba Group +1

  26. On Effectiveness and Efficiency of Agentic Tool-calling and RL Training

    May 28, 2026Tong Liu, Cheng Qian, Matej Cief +4Agentic Reinforcement LearningTool Invocation

    1LMU Munich & Munich Center for Machine Learning · 2UIUC · 3Amazon +1

  27. Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement

    May 26, 2026Dingwei Chen, Zefang Zong, Zhipeng Ma +5Agentic Reinforcement LearningAgentic Benchmarks

    Tencent Inc · The Chinese University of Hong Kong · Shenzhen MSU-BIT University

  28. Tool-Call Dependency Structure is Linearly Decodable in LLM Agent Residual Streams

    May 25, 2026Tianda Sun, Dimitar KazakovDependency GraphLarge Language Model Agents

    University of York Department of Computer Science Heslington, York YO10 5DD

  29. Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval

    May 22, 2026Michal Shlapentokh-Rothman, Prachi Garg, Yu-Xiong Wang +1Long Video Question AnsweringKeyframe Selection

    University of Illinois at Urbana-Champaign

  30. Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs

    May 17, 2026Yuxuan Lu, Ziyi Wang, Yingzhou Lu +12CallLarge Language Model Tool Use

    Northeastern University · Independent Researcher

  31. ContractBench: Can LLM Agents Preserve Observation Contracts?

    May 17, 2026Jicheng Wang, Yifeng He, Zili Wang +3ContractsLarge Language Model Agents

    University of California, Davis · University of Southern California · University of Hong Kong

  32. An Efficient Machine Learning-based Framework for Detection and Prevention of Frauds in Telecom Networks

    May 17, 2026Praveen Hegde, Mishal ShahMobile NetworksFraud Detection

    Associate Director-Emerging Commercial Platforms Verizon Atlanta, USA · Senior Software Engineer Bloomberg LP Jersey City, USA

  33. To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents

    May 16, 2026Wei Shi, Ziheng Peng, Sihang Li +4CallLarge Language Model Agents

    Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · Renmin University of China +2

  34. Nice Fold or Hero Call: Learning Budget-Efficient Thinking for Adaptive Reasoning

    May 12, 2026Zhaomeng Zhou, Lan Zhang, Junyang Wang +2Reasoning SkillsToken Budget Allocation

    University of Science and Technology of China · The Chinese University of Hong Kong

  35. Tool Calling is Linearly Readable and Steerable in Language Models

    May 8, 2026Zekun Wu, Ze Wang, Seonglae Cho +4CallInstruction-Tuned Models

    University College London · Holistic AI · Imperial College London

  36. Two Calls, Two Moments, and the Vote-Accuracy Curve of Repeated LLM Inference

    May 5, 2026Yi LiuMajority VotingLLM Inference Optimization

    York University

  37. From Birdsong to Rumbles: Classifying Elephant Calls with Out-of-Species Embeddings

    Apr 30, 2026Christiaan M. Geldenhuys, Thomas R. NieslerAnimal VocalizationsAcoustic

    Department of Electrical and Electronic Engineering University of Stellenbosch

  38. Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing

    Apr 24, 2026Michael Lan, Narmeen Fatimah Oozeer, Chaithanya Bandi +4Artificial Intelligence SafetyModel Auditing

    Martian · University of Delaware · MATS +2