tool calling

Assertion-Conditioned Compliance: A Provenance-Aware Vulnerability in Multi-Turn Tool-Calling Agents EACL 2026 CodeDance: A Dynamic Tool-integrated MLLM for Executable Visual Reasoning CVPR 2026 DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning EACL 2026 Live API-Bench: 2500+ Live APIs for Testing Multi-Step Tool Calling EACL 2026 LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling CVPR 2026 Lost in Execution: On the Multilingual Robustness of Tool Calling in Large Language Models ACL 2026 rosaOS: Agentic Operating System for Embodied LLMs ACL 2026 Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents ACL 2026 CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios EMNLP 2025 Divergent Thoughts toward One Goal: LLM-based Multi-Agent Collaboration System for Electronic Design Automation NAACL 2025 Enhancing Tool Learning in Large Language Models with Hierarchical Error Checklists ACL 2025 From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection NAACL 2025 LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback ACL 2025 NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls EMNLP 2025 NesTools: A Dataset for Evaluating Nested Tool Learning Abilities of Large Language Models COLING 2025 SCRIBE: Structured Chain Reasoning for Interactive Behaviour Explanations using Tool Calling EMNLP 2025 Sparse Rewards Can Self-Train Dialogue Agents ACL 2025 Tool Calling for Arabic LLMs: Data Strategies and Instruction Tuning EMNLP 2025 TOOL-ED: Enhancing Empathetic Response Generation with the Tool Calling Capability of LLM COLING 2025 ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis NAACL 2025 ToolGen: Unified Tool Retrieval and Calling via Generation ICLR 2025 Tool Preferences in Agentic LLMs are Unreliable EMNLP 2025 ToolReflection: Improving Large Language Models for Real-World API Calls with Self-Generated Data ACL 2025 When2Call: When (not) to Call Tools NAACL 2025 OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer EMNLP 2024