Agent Systems

Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planning NAACL 2025 Snap Out of It: A Dual-Process Approach to Mitigating Overthinking in Language Model Reasoning ACL 2025 SocialForge: simulating the social internet to provide realistic training against influence operations ACL 2025 Social Intelligence in the Age of LLMs NAACL 2025 Socratic Style Chain-of-Thoughts Help LLMs to be a Better Reasoner ACL 2025 SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters CVPR 2025 SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATION ICLR 2025 SPARK: Simulating the Co-evolution of Stance and Topic Dynamics in Online Discourse with LLM-based Agents EMNLP 2025 Sparse Rewards Can Self-Train Dialogue Agents ACL 2025 Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulation CVPR 2025 SPeCtrum: A Grounded Framework for Multidimensional Identity Representation in LLM-Based Agent NAACL 2025 Speculative Reward Model Boosts Decision Making Ability of LLMs Cost-Effectively ACL 2025 Spiral of Silence in Large Language Model Agents EMNLP 2025 SpiritSight Agent: Advanced GUI Agent with One Look CVPR 2025 StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs ACL 2025 STACKFEED: Structured Textual Actor-Critic Knowledge base editing with FEEDback EMNLP 2025 STA-CoT: Structured Target-Centric Agentic Chain-of-Thought for Consistent Multi-Image Geological Reasoning EMNLP 2025 START: Self-taught Reasoner with Tools EMNLP 2025 StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking ACL 2025 State-Based Disassembly Planning AAAI 2025 STDArm: Transfer Visuomotor Policy From Static Data Training to Dynamic Robot Manipulation RSS 2025 STeCa: Step-level Trajectory Calibration for LLM Agent Learning ACL 2025 StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization EMNLP 2025 STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning ICLR 2025 STREAQ: Selective Tiered Routing for Effective and Affordable Contact Center Quality Assurance EMNLP 2025