inference cost

AutoTool: Efficient Tool Selection for Large Language Model Agents AAAI 2026 Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning AAAI 2026 MTRouter: Cost-Aware Multi-Turn LLM Routing with History–Model Joint Embeddings ACL 2026 Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models ACL 2026 Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities AAAI 2026 Answer Convergence as a Signal for Early Stopping in Reasoning EMNLP 2025 Are Optimal Algorithms Still Optimal? Rethinking Sorting in LLM-Based Pairwise Ranking with Batching and Caching ACL 2025 GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression EMNLP 2025 Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers ICML 2025 Let LLM Tell What to Prune and How Much to Prune ICML 2025 Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning NAACL 2025 No Need to Talk: Asynchronous Mixture of Language Models ICLR 2025 Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models ICML 2025 Prompt-based Depth Pruning of Large Language Models ICML 2025 RouteLLM: Learning to Route LLMs from Preference Data ICLR 2025 Scalable and Cost Effective High-Cardinality Classification with LLMs via Multi-View Label Representations and Retrieval Augmentation EMNLP 2025 Select-then-Route : Taxonomy guided Routing for LLMs EMNLP 2025 SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context EMNLP 2025 TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers’ Guidance EMNLP 2025 You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQL NAACL 2025 Breaking ReLU Barrier: Generalized MoEfication for Dense Pretrained Models EMNLP 2024 Divide-or-Conquer? Which Part Should You Distill Your LLM? EMNLP 2024 Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion NeurIPS 2024 From Sparse to Soft Mixtures of Experts ICLR 2024 Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs ACL 2024