{"total":27,"rows":[{"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":"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":"2504.00762","title":"Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute","created":"2025-04-01","cited_by_count":20,"area":"lr"},{"id":"2509.03817","title":"Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learning","created":"2025-09-04","cited_by_count":18,"area":"lr"},{"id":"2602.02823","title":"R2-Router: A New Paradigm for LLM Routing with Reasoning","created":"2026-02-02","cited_by_count":14,"area":"lr"},{"id":"2509.21164","title":"Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say","created":"2025-09-25","cited_by_count":12,"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":"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":"2509.09864","title":"Latency and Token-Aware Test-Time Compute","created":"2025-09-11","cited_by_count":8,"area":"lr"},{"id":"2601.05167","title":"RelayLLM: Efficient Reasoning via Collaborative Decoding","created":"2026-01-08","cited_by_count":8,"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":"2607.17384","title":"Quantifying Diversity of Thought: A Predictive Law of Weighted LLM Ensemble Lift","created":"2026-07-19","cited_by_count":5,"area":"lr"},{"id":"2601.06022","title":"AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs","created":"2026-01-09","cited_by_count":4,"area":"lr"},{"id":"2601.22323","title":"Models Under SCOPE: Scalable and Controllable Routing via Pre-hoc Reasoning","created":"2026-01-29","cited_by_count":4,"area":"lr"},{"id":"2602.22556","title":"Stable Adaptive Thinking via Advantage Shaping and Length-Aware Gradient Regulation","created":"2026-02-26","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":"2605.10805","title":"Reasoning Is Not Free: Robust Adaptive Cost-Efficient Routing for LLM-as-a-Judge","created":"2026-05-11","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":"2506.21638","title":"R1-Ranker: Teaching LLM Rankers to Reason","created":"2025-06-25","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":"2604.13757","title":"Rethinking AI Hardware: A Three-Layer Cognitive Architecture for Autonomous Agents","created":"2026-04-15","cited_by_count":0,"area":"lr"},{"id":"2608.10441","title":"Detecting an Effect Is Not Learning to Act on It: A Reward-SNR Floor for LLM Acquisition Agents","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.13315","title":"Keep, Customize, or Exit: Default Design and Token Pricing in LLM Reasoning Services","created":"2026-08-13","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":"2609.23085","title":"Measured Joules, Learned Routes: Learning to Route for Energy-Efficient LLM Serving","created":"2026-09-19","cited_by_count":0,"area":"lr"}],"next_cursor":null}