Agent Systems

Meta-Reasoning Improves Tool Use in Large Language Models NAACL 2025 Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge EMNLP 2025 Meta-Tool: Unleash Open-World Function Calling Capabilities of General-Purpose Large Language Models ACL 2025 MICE for CATs: Model-Internal Confidence Estimation for Calibrating Agents with Tools NAACL 2025 Micro-Act: Mitigate Knowledge Conflict in Question Answering via Actionable Self-Reasoning ACL 2025 Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models ACL 2025 Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models ICLR 2025 MIRAGE: Exploring How Large Language Models Perform in Complex Social Interactive Environments ACL 2025 Mirror in the Model: Ad Banner Image Generation via Reflective Multi-LLM and Multi-modal Agents EMNLP 2025 MIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool Learning IJCAI 2025 MIRROR: Multimodal Cognitive Reframing Therapy for Rolling with Resistance EMNLP 2025 Mis-prompt: Benchmarking Large Language Models for Proactive Error Handling ACL 2025 MistSense: Versatile Online Detection of Procedural and Execution Mistakes ICCV 2025 Mixture of Knowledge Minigraph Agents for Literature Review Generation AAAI 2025 Mixture-of-Personas Language Models for Population Simulation ACL 2025 MLDebugging: Towards Benchmarking Code Debugging Across Multi-Library Scenarios ACL 2025 MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering ICLR 2025 MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents ICLR 2025 MLLM-Tool: A Multimodal Large Language Model for Tool Agent Learning WACV 2025 MMAT-1M: A Large Reasoning Dataset for Multimodal Agent Tuning ICCV 2025 MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains NAACL 2025 MMInA: Benchmarking Multihop Multimodal Internet Agents ACL 2025 MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents ICLR 2025 MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation NAACL 2025 MobileA3gent: Training Mobile GUI Agents Using Decentralized Self-Sourced Data from Diverse Users EMNLP 2025