{"total":98,"rows":[{"id":"2406.04692","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","created":"2024-06-07","cited_by_count":438,"area":"lr"},{"id":"2310.03094","title":"Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning","created":"2023-10-04","cited_by_count":143,"area":"lr"},{"id":"2305.11860","title":"Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs","created":"2023-05-19","cited_by_count":115,"area":"lr"},{"id":"2308.10379","title":"Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models","created":"2023-08-20","cited_by_count":92,"area":"lr"},{"id":"2405.10825","title":"Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities","created":"2024-05-17","cited_by_count":83,"area":"lr"},{"id":"2506.17211","title":"BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning","created":"2025-06-20","cited_by_count":63,"area":"lr"},{"id":"2309.06553","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","created":"2023-09-13","cited_by_count":37,"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":"2502.04392","title":"Division-of-Thoughts: Harnessing Hybrid Language Model Synergy for Efficient On-Device Agents","created":"2025-02-06","cited_by_count":25,"area":"lr"},{"id":"2502.15964","title":"Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models","created":"2025-02-21","cited_by_count":20,"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":"2309.13075","title":"SCREWS: A Modular Framework for Reasoning with Revisions","created":"2023-09-20","cited_by_count":16,"area":"lr"},{"id":"2505.07961","title":"Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement","created":"2025-05-12","cited_by_count":14,"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":"2402.02563","title":"Synergy-of-Thoughts: Eliciting Efficient Reasoning in Hybrid Language Models","created":"2024-02-04","cited_by_count":13,"area":"lr"},{"id":"2506.05901","title":"Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router","created":"2025-06-06","cited_by_count":13,"area":"lr"},{"id":"2409.07355","title":"Think Together and Work Better: Combining Humans' and LLMs' Think-Aloud Outcomes for Effective Text Evaluation","created":"2024-09-11","cited_by_count":12,"area":"lr"},{"id":"2510.08731","title":"When to Reason: Semantic Router for vLLM","created":"2025-10-09","cited_by_count":12,"area":"lr"},{"id":"2402.16844","title":"Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding","created":"2024-02-26","cited_by_count":11,"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":"2603.12634","title":"Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents","created":"2026-03-13","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":"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":"2506.11578","title":"Efficient LLM Collaboration via Planning","created":"2025-06-13","cited_by_count":7,"area":"lr"},{"id":"2507.02822","title":"SynapseRoute: An Auto-Route Switching Framework on Dual-State Large Language Model","created":"2025-07-03","cited_by_count":7,"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":"2510.05077","title":"Slm-mux: Orchestrating small language models for reasoning","created":"2025-10-06","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":"2603.16219","title":"SpecSteer: Synergizing Local Context and Global Reasoning for Efficient Personalized Generation","created":"2026-03-17","cited_by_count":6,"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":"2511.01650","title":"EngTrace: A Symbolic Benchmark for Verifiable Process Supervision of Engineering Reasoning","created":"2025-11-03","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":"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":"2508.03333","title":"CTTS: Collective Test-Time Scaling","created":"2025-08-05","cited_by_count":3,"area":"lr"},{"id":"2508.15754","title":"When Tools Hurt LLM Reasoning: State-Dependent Belief Revision under External Evidence","created":"2025-08-21","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":"2605.08876","title":"OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents","created":"2026-05-09","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":"2310.10686","title":"Autonomous Tree-search Ability of Large Language Models","created":"2023-10-14","cited_by_count":2,"area":"lr"},{"id":"2410.15135","title":"TrendFact: A Benchmark Towards Hotspot Perception in Automatic Fact-Checking","created":"2024-10-19","cited_by_count":2,"area":"lr"},{"id":"2511.07397","title":"Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents","created":"2025-11-10","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":"2605.10805","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":"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":"2607.08065","title":"When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals","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":"2609.36059","title":"Mnemon: Raw Records, Fast Judgments, Slow Thoughts","created":"2026-09-28","cited_by_count":2,"area":"lr"},{"id":"2508.08115","title":"TeamMedAgents: Pareto-Efficient Multi-Agent Medical Reasoning Through Teamwork Theory","created":"2025-08-11","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":"2603.25498","title":"EcoThink: A Green Adaptive Inference Framework for Sustainable and Accessible Agents","created":"2026-03-26","cited_by_count":1,"area":"lr"},{"id":"2604.25931","title":"Anchored Confabulation: Partial Evidence Non-Monotonically Amplifies Confident Hallucination in LLMs","created":"2026-04-02","cited_by_count":1,"area":"lr"},{"id":"2605.07686","title":"The Coupling Tax: How Shared Token Budgets Undermine Visible Chain-of-Thought Under Fixed Output Limits","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.27712","title":"Prefix-Safe Bayesian Belief Tracking for LLM Reasoning Reliability:Separating Calibration from Ranking","created":"2026-05-26","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":"2607.06906","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":"2610.09683","title":"System Switch: When Should a Fast Decision Model Stop and Think?","created":"2026-10-07","cited_by_count":1,"area":"lr"},{"id":"2507.14406","title":"Fail Fast, or Ask: Mitigating the Deficiencies of Reasoning LLMs with Human-in-the-Loop Systems Engineering","created":"2025-07-18","cited_by_count":0,"area":"lr"},{"id":"2601.00823","title":"Energy-Aware Routing to Large Reasoning Models","created":"2025-12-23","cited_by_count":0,"area":"lr"},{"id":"2601.08679","title":"PersonaDual: Balancing Personalization and Objectivity via Adaptive Reasoning","created":"2026-01-13","cited_by_count":0,"area":"lr"},{"id":"2601.19302","title":"Formula-One Prompting: A Composable Equation-First Prefix for Applied Mathematics","created":"2026-01-27","cited_by_count":0,"area":"lr"},{"id":"2602.09173","title":"$n$-Musketeers: Reinforcement Learning Shapes Collaboration Among Language Models","created":"2026-02-09","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":"2603.27571","title":"RAGent: Physics-Aware Agentic Reasoning for Training-Free mmWave Human Activity Recognition","created":"2026-03-29","cited_by_count":0,"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":"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":"2605.02472","title":"Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudication","created":"2026-05-04","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":"2605.29319","title":"Rethinking Stepwise Model Routing: A Cost-Efficient Table Reasoning Perspective","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2606.06745","title":"When to Think Deeply: Inhibitory Deliberation for LLM Reasoning","created":"2026-06-04","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":"2606.24937","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2608.07424","title":"CoBa: Cost-Effective Test-Time Scaling via Compute-Balanced Routing","created":"2026-08-07","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":"2609.00738","title":"Escaping Redundant Reasoning: Structure-Aware Search for Inference-Time LLMs","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2609.29548","title":"Certified Predictive Value-of-Advice Gating for Cost-Aware Language-Model Guidance in Reinforcement Learning","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2609.33119","title":"MedRouter: Demystifying Knowledge Differences Across Medical LLMs for Routing-Based Reasoning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.35833","title":"Neurosymbolic Routing for Reliable Reasoning on Resource-Constrained Edge Devices","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"id":"2610.07716","title":"Readout Stability in Prefill-Only Decision Models:Zero-Label Prediction and Inference-Time Compute Allocation","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.11978","title":"Specialized Decision Models vs. General-Purpose LLMs: Benchmarking Jev Across Knowledge, Reasoning, and Multilingual Tasks","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.17456","title":"Compositional RL: Evaluating and Training LLMs for Collaborative Reasoning","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.17869","title":"ECMR: Evidence-Aware Deliberation Control for Multi-Agent LLM Reasoning","created":"2026-10-13","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"},{"id":"2610.20057","title":"Beyond Correctness: Compute-Responsive Data Selection for Reasoning Model Post-Training","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}