{"total":41,"rows":[{"id":"2412.18547","title":"Token-Budget-Aware LLM Reasoning","created":"2024-12-24","cited_by_count":247,"area":"lr"},{"id":"2503.09501","title":"ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning","created":"2025-03-12","cited_by_count":79,"area":"lr"},{"id":"2508.02120","title":"Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models","created":"2025-08-04","cited_by_count":37,"area":"lr"},{"id":"2503.24377","title":"Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models","created":"2025-03-31","cited_by_count":36,"area":"lr"},{"id":"2505.19435","title":"Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection","created":"2025-05-26","cited_by_count":23,"area":"lr"},{"id":"2507.09662","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","created":"2025-07-13","cited_by_count":18,"area":"lr"},{"id":"2601.05110","title":"GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts","created":"2026-01-08","cited_by_count":17,"area":"lr"},{"id":"2602.09924","title":"LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations","created":"2026-02-10","cited_by_count":14,"area":"lr"},{"id":"2508.11582","title":"Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models","created":"2025-08-15","cited_by_count":13,"area":"lr"},{"id":"2505.12601","title":"Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers","created":"2025-05-19","cited_by_count":11,"area":"lr"},{"id":"2504.18116","title":"Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models","created":"2025-04-25","cited_by_count":9,"area":"lr"},{"id":"2511.06190","title":"Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning","created":"2025-11-09","cited_by_count":9,"area":"lr"},{"id":"2604.14853","title":"Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization","created":"2026-04-16","cited_by_count":9,"area":"lr"},{"id":"2601.05167","title":"RelayLLM: Efficient Reasoning via Collaborative Decoding","created":"2026-01-08","cited_by_count":8,"area":"lr"},{"id":"2601.10245","title":"TRIM: Hybrid Inference via Targeted Stepwise Routing in Multi-Step Reasoning Tasks","created":"2026-01-15","cited_by_count":8,"area":"lr"},{"id":"2506.17336","title":"PPMI: Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases","created":"2025-06-19","cited_by_count":6,"area":"lr"},{"id":"2509.25426","title":"RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMs","created":"2025-09-29","cited_by_count":6,"area":"lr"},{"id":"2503.21464","title":"Harnessing Chain-of-Thought Metadata for Task Routing and Adversarial Prompt Detection","created":"2025-03-27","cited_by_count":5,"area":"lr"},{"id":"2509.24050","title":"Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training","created":"2025-09-28","cited_by_count":5,"area":"lr"},{"id":"2604.05164","title":"Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning in Agents","created":"2026-04-06","cited_by_count":4,"area":"lr"},{"id":"2511.03808","title":"Optimizing Reasoning Efficiency through Prompt Difficulty Prediction","created":"2025-11-05","cited_by_count":3,"area":"lr"},{"id":"2604.15075","title":"Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap","created":"2026-04-16","cited_by_count":3,"area":"lr"},{"id":"2606.04402","title":"Not All Errors Are Equal: Consequence-Aware Reasoning Compute Allocation","created":"2026-06-03","cited_by_count":3,"area":"lr"},{"id":"2606.06924","title":"From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing","created":"2026-06-05","cited_by_count":3,"area":"lr"},{"id":"2512.15089","title":"Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Models","created":"2025-12-17","cited_by_count":2,"area":"lr"},{"id":"2602.05307","title":"MentorCollab: Large-to-Small Inference-Time Mentorship for Concise Reasoning in Language Models","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2602.15843","title":"The Perplexity Paradox: Why Code Compresses Better Than Math in LLM Prompts","created":"2026-01-21","cited_by_count":2,"area":"lr"},{"id":"2605.11301","title":"LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?","created":"2026-05-11","cited_by_count":2,"area":"lr"},{"id":"2607.08940","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2512.03667","title":"Colon-X: Advancing Intelligent Colonoscopy toward Clinical Reasoning","created":"2025-12-03","cited_by_count":1,"area":"lr"},{"id":"2604.16694","title":"RankGuide: Tensor-Rank-Guided Routing and Steering for Efficient Reasoning","created":"2026-04-17","cited_by_count":1,"area":"lr"},{"id":"2605.30898","title":"UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2607.20327","title":"PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference","created":"2026-07-22","cited_by_count":1,"area":"lr"},{"id":"2510.22909","title":"Rethinking Inference Placement for Deep Learning across Edge and Cloud Platforms: A Multi-Objective Optimization Perspective and Future Directions","created":"2025-10-27","cited_by_count":0,"area":"lr"},{"id":"2603.05818","title":"RouteGoT: Node-Adaptive Routing for Cost-Efficient Graph of Thoughts Reasoning","created":"2026-03-06","cited_by_count":0,"area":"lr"},{"id":"2603.13612","title":"LLM Routing as Reasoning: A MaxSAT View","created":"2026-03-13","cited_by_count":0,"area":"lr"},{"id":"2605.06116","title":"Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2606.15308","title":"Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades","created":"2026-06-13","cited_by_count":0,"area":"lr"},{"id":"2606.15872","title":"SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks","created":"2026-06-14","cited_by_count":0,"area":"lr"},{"id":"2608.15817","title":"RLCascadeRouter: Quality-Estimator-Free Cascade Routing via Reinforcement Learning","created":"2026-08-16","cited_by_count":0,"area":"lr"},{"id":"2610.18566","title":"Rethinking Quality in Large Language Model Routing: Security-Conditioned Model-and-Budget Selection","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}