{"total":117,"rows":[{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464,"area":"lr"},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2504.15895","title":"Dynamic Early Exit in Reasoning Models","created":"2025-04-22","cited_by_count":219,"area":"lr"},{"id":"2504.09858","title":"Reasoning Models Can Be Effective Without Thinking","created":"2025-04-14","cited_by_count":187,"area":"lr"},{"id":"2503.21614","title":"A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond","created":"2025-03-27","cited_by_count":132,"area":"lr"},{"id":"2505.13379","title":"Thinkless: LLM Learns When to Think","created":"2025-05-19","cited_by_count":113,"area":"lr"},{"id":"2505.15436","title":"Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs","created":"2025-05-21","cited_by_count":96,"area":"lr"},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95,"area":"lr"},{"id":"2505.07686","title":"S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models","created":"2025-05-12","cited_by_count":87,"area":"lr"},{"id":"2503.23077","title":"Efficient Inference for Large Reasoning Models: A Survey","created":"2025-03-29","cited_by_count":61,"area":"lr"},{"id":"2505.11274","title":"SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning","created":"2025-05-16","cited_by_count":48,"area":"lr"},{"id":"2506.02536","title":"Answer Convergence as a Signal for Early Stopping in Reasoning","created":"2025-06-03","cited_by_count":40,"area":"lr"},{"id":"2505.03469","title":"Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models","created":"2025-05-06","cited_by_count":39,"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":"2609.26550","title":"JEV-as-a-Judge: Accept When Confident, Escalate When Unsure","created":"2026-09-22","cited_by_count":30,"area":"lr"},{"id":"2505.12284","title":"Shorten After You're Right: Lazy Length Penalties for Reasoning RL","created":"2025-05-18","cited_by_count":25,"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":"2410.05563","title":"Rational Metareasoning for Large Language Models","created":"2024-10-07","cited_by_count":20,"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":"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":"2506.02397","title":"OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation","created":"2025-06-03","cited_by_count":17,"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":"2512.01992","title":"LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess","created":"2025-12-01","cited_by_count":15,"area":"lr"},{"id":"2508.00574","title":"SynAdapt: Learning Adaptive Reasoning in Large Language Models via Synthetic Continuous Chain-of-Thought","created":"2025-08-01","cited_by_count":13,"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":"2510.08731","title":"When to Reason: Semantic Router for vLLM","created":"2025-10-09","cited_by_count":12,"area":"lr"},{"id":"2511.10788","title":"From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models","created":"2025-11-13","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":"2507.15758","title":"LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization","created":"2025-07-21","cited_by_count":11,"area":"lr"},{"id":"2510.09913","title":"Don't Throw Away Your Pretrained Model","created":"2025-10-10","cited_by_count":10,"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":"2505.20664","title":"Self-Route: Automatic Mode Switching via Capability Estimation for Efficient Reasoning","created":"2025-05-27","cited_by_count":8,"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":"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":"2603.07915","title":"Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents","created":"2026-03-09","cited_by_count":8,"area":"lr"},{"id":"2604.02967","title":"FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models","created":"2026-04-03","cited_by_count":8,"area":"lr"},{"id":"2510.05593","title":"Improving Chain-of-Thought Efficiency for Autoregressive Image Generation","created":"2025-10-07","cited_by_count":7,"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":"2510.05077","title":"Slm-mux: Orchestrating small language models for reasoning","created":"2025-10-06","cited_by_count":6,"area":"lr"},{"id":"2510.09133","title":"On the Provable Performance Guarantee of Efficient Reasoning Models","created":"2025-10-10","cited_by_count":6,"area":"lr"},{"id":"2601.21418","title":"Mitigating Overthinking in Large Reasoning Models via Difficulty-aware Reinforcement Learning","created":"2026-01-29","cited_by_count":6,"area":"lr"},{"id":"2602.11931","title":"AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection","created":"2026-02-12","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":"2507.00004","title":"A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search","created":"2025-06-10","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":"2602.01797","title":"ORCH: many analyses, one merge-a deterministic multi-agent orchestrator for discrete-choice reasoning with EMA-guided routing","created":"2026-02-02","cited_by_count":5,"area":"lr"},{"id":"2603.20895","title":"LLM Router: Rethinking Routing with Prefill Activations","created":"2026-03-21","cited_by_count":5,"area":"lr"},{"id":"2512.23213","title":"Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process","created":"2025-12-29","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":"2603.03752","title":"Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning","created":"2026-03-04","cited_by_count":4,"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":"2508.15507","title":"Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning","created":"2025-08-21","cited_by_count":3,"area":"lr"},{"id":"2509.23633","title":"Fast Thinking for Large Language Models","created":"2025-09-28","cited_by_count":3,"area":"lr"},{"id":"2512.03057","title":"A note on conditional PAC-efficient reasoning in large language model routing","created":"2025-11-25","cited_by_count":3,"area":"lr"},{"id":"2603.11781","title":"From Debate to Deliberation: Structured Collective Reasoning with Typed Epistemic Acts","created":"2026-03-12","cited_by_count":3,"area":"lr"},{"id":"2603.17729","title":"SARE: Sample-wise Adaptive Reasoning for Training-free Fine-grained Visual Recognition","created":"2026-03-18","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":"2604.26940","title":"Select to Think: Unlocking SLM Potential with Local Sufficiency","created":"2026-04-29","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":"2607.13034","title":"Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution","created":"2026-07-14","cited_by_count":3,"area":"lr"},{"id":"2608.25992","title":"ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs","created":"2026-08-26","cited_by_count":3,"area":"lr"},{"id":"2508.21762","title":"Reasoning-Intensive Regression","created":"2025-08-29","cited_by_count":2,"area":"lr"},{"id":"2510.21007","title":"Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?","created":"2025-10-23","cited_by_count":2,"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":"2604.11045","title":"Sema Code: Decoupling AI Coding Agents into Programmable, Embeddable Infrastructure","created":"2026-04-13","cited_by_count":2,"area":"lr"},{"id":"2605.08070","title":"VecCISC: Improving Confidence-Informed Self-Consistency with Reasoning Trace Clustering and Candidate Answer Selection","created":"2026-05-08","cited_by_count":2,"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":"2605.16874","title":"Reasoning Can Be Restored by Correcting a Few Decision Tokens","created":"2026-05-16","cited_by_count":2,"area":"lr"},{"id":"2605.29310","title":"Rubric-Guided Process Reward for Stepwise Model Routing","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2606.03092","title":"The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs","created":"2026-06-02","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":"2607.26865","title":"Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents","created":"2026-07-29","cited_by_count":2,"area":"lr"},{"id":"2608.04771","title":"Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning","created":"2026-08-05","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":"2602.06454","title":"RelayGen: Intra-Generation Model Switching for Efficient Reasoning","created":"2026-02-06","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":"2606.19808","title":"Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning","created":"2026-06-18","cited_by_count":1,"area":"lr"},{"id":"2606.31285","title":"Spatial Reasoning via Modality Switching Between Language and Symbolic Representations","created":"2026-06-30","cited_by_count":1,"area":"lr"},{"id":"2607.06906","title":"The Harness Effect: How Orchestration Design Sets the Token Economics of Enterprise Agentic AI","created":"2026-07-08","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":"2609.33052","title":"BudgetVerify: Budget-Tiered Verification for Financial QA","created":"2026-09-27","cited_by_count":1,"area":"lr"},{"id":"2512.14332","title":"Step-Tagging: Toward controlling the generation of Language Reasoning Models through step monitoring","created":"2025-12-16","cited_by_count":0,"area":"lr"},{"id":"2601.11252","title":"Beyond Model Scaling: Test-Time Intervention for Efficient Deep Reasoning","created":"2026-01-16","cited_by_count":0,"area":"lr"},{"id":"2603.12669","title":"Vision Verification Enhanced Fusion of VLMs for Efficient Visual Reasoning","created":"2026-03-13","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":"2604.14214","title":"CROP: Token-Efficient Reasoning in Large Language Models via Regularized Prompt Optimization","created":"2026-04-08","cited_by_count":0,"area":"lr"},{"id":"2604.17450","title":"Compiling Deterministic Structure into SLM Harnesses","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2604.21057","title":"TRACES: Tagging Reasoning Steps for Adaptive Cost-Efficient Early-Stopping","created":"2026-04-22","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":"2605.30837","title":"Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense","created":"2026-05-29","cited_by_count":0,"area":"lr"},{"id":"2606.00532","title":"KACE: Knowledge-Adaptive Context Engineering for Mathematical Reasoning","created":"2026-05-30","cited_by_count":0,"area":"lr"},{"id":"2606.03236","title":"Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile Agents","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2606.12479","title":"ReCal: Reward Calibration for RL-based LLM Routing","created":"2026-06-10","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}