token efficiency

Augmented Runtime Collaboration for Self-Organizing Multi-Agent Systems: A Hybrid Bi-Criteria Routing Approach AAAI 2026 Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Significant Gains in Reasoning Efficiency in Large Language Models AAAI 2026 Beyond Markovian Forgetfulness: Episodic Memory for Reasoning-Intensive Retrieval ACL 2026 Cost-Effective Communication: An Auction-based Method for Language Agent Interaction AAAI 2026 Delta-LLaVA: Base-then-Specialize Alignment for Token-Efficient Vision-Language Models WACV 2026 iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference AAAI 2026 LLM-as-Scheduler: Agentic Workflow Dynamic Scheduling ACL 2026 MoSs: Mixture of Scales for Efficient High-Resolution Autoregressive Image Generation AAAI 2026 SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning ACL 2026 SSM-Aware Token-Efficient VMamba via Adaptive Patch Pruning and Merging for Person Re-Identification CVPR 2026 AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration ACL 2025 Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts ACL 2025 CIFLEX: Contextual Instruction Flow for Sub-task Execution in Multi-Turn Interactions with a Single On-Device LLM EMNLP 2025 Context Filtering with Reward Modeling in Question Answering COLING 2025 Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems ICLR 2025 DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs ICCV 2025 Distilling Many-Shot In-Context Learning into a Cheat Sheet EMNLP 2025 EcoTune: Token-Efficient Multi-Fidelity Hyperparameter Optimization for Large Language Model Inference EMNLP 2025 EfficientXLang: Towards Improving Token Efficiency Through Cross-Lingual Reasoning EMNLP 2025 EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models NAACL 2025 GraphRAG: Leveraging Graph-Based Efficiency to Minimize Hallucinations in LLM-Driven RAG for Finance Data COLING 2025 JSON Whisperer: Efficient JSON Editing with LLMs EMNLP 2025 MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens ACL 2025 mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding ACL 2025 Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation NAACL 2025