{"total":70,"rows":[{"id":"2508.15260","title":"Deep Think with Confidence","created":"2025-08-21","cited_by_count":205,"area":"lr"},{"id":"2508.09726","title":"Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning","created":"2025-08-13","cited_by_count":75,"area":"lr"},{"id":"2507.14417","title":"Inverse Scaling in Test-Time Compute","created":"2025-07-19","cited_by_count":50,"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":"2505.23590","title":"Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles","created":"2025-05-29","cited_by_count":36,"area":"lr"},{"id":"2509.19284","title":"What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT","created":"2025-09-23","cited_by_count":25,"area":"lr"},{"id":"2602.13517","title":"Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens","created":"2026-02-13","cited_by_count":22,"area":"lr"},{"id":"2510.10409","title":"Trace Length is a Simple Uncertainty Signal in Reasoning Models","created":"2025-10-12","cited_by_count":19,"area":"lr"},{"id":"2602.08354","title":"Does Your Reasoning Model Implicitly Know When to Stop Thinking?","created":"2026-02-09","cited_by_count":19,"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":"2603.09906","title":"Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs","created":"2026-03-10","cited_by_count":16,"area":"lr"},{"id":"2509.13990","title":"Slim-SC: Thought Pruning for Efficient Scaling with Self-Consistency","created":"2025-09-17","cited_by_count":13,"area":"lr"},{"id":"2512.21540","title":"Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model","created":"2025-12-25","cited_by_count":13,"area":"lr"},{"id":"2512.02008","title":"The Art of Scaling Test-Time Compute for Large Language Models","created":"2025-12-01","cited_by_count":12,"area":"lr"},{"id":"2508.21787","title":"PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains","created":"2025-08-29","cited_by_count":10,"area":"lr"},{"id":"2510.07880","title":"Do LLMs Really Need 10+ Thoughts for \"Find the Time 1000 Days Later\"? Towards Structural Understanding of LLM Overthinking","created":"2025-10-09","cited_by_count":10,"area":"lr"},{"id":"2606.00206","title":"Quantized Reasoning Models Think They Need to Think Longer, but They Do Not","created":"2026-05-29","cited_by_count":10,"area":"lr"},{"id":"2509.07339","title":"Performative Thinking? The Brittle Correlation Between CoT Length and Problem Complexity","created":"2025-09-09","cited_by_count":9,"area":"lr"},{"id":"2510.10494","title":"Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning","created":"2025-10-12","cited_by_count":9,"area":"lr"},{"id":"2510.14943","title":"LaSeR: Reinforcement Learning with Last-Token Self-Rewarding","created":"2025-10-16","cited_by_count":9,"area":"lr"},{"id":"2512.00218","title":"Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability?","created":"2025-11-28","cited_by_count":9,"area":"lr"},{"id":"2602.08332","title":"Latent Reasoning with Supervised Thinking States","created":"2026-02-09","cited_by_count":9,"area":"lr"},{"id":"2511.20048","title":"Reducing Latency of LLM Search Agent via Speculation-based Algorithm-System Co-Design","created":"2025-11-25","cited_by_count":8,"area":"lr"},{"id":"2601.11340","title":"Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models","created":"2026-01-16","cited_by_count":8,"area":"lr"},{"id":"2608.05131","title":"OPD-V: Visual On-Policy Self-Distillation with Modality Balance","created":"2026-08-05","cited_by_count":8,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2604.01348","title":"Procedural Knowledge at Scale Improves Reasoning","created":"2026-04-01","cited_by_count":7,"area":"lr"},{"id":"2509.12434","title":"Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization","created":"2025-09-15","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":"2512.19081","title":"Population-Evolve: a Parallel Sampling and Evolutionary Method for LLM Math Reasoning","created":"2025-12-22","cited_by_count":6,"area":"lr"},{"id":"2601.19928","title":"Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2608.03972","title":"ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning","created":"2026-08-04","cited_by_count":6,"area":"lr"},{"id":"2509.21549","title":"Correct Reasoning Paths Visit Shared Decision Pivots","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2510.08026","title":"PEAR: Phase Entropy Aware Reward for Efficient Reasoning","created":"2025-10-09","cited_by_count":5,"area":"lr"},{"id":"2601.03066","title":"Do LLMs Encode Functional Importance of Reasoning Tokens?","created":"2026-01-06","cited_by_count":5,"area":"lr"},{"id":"2602.14798","title":"Overthinking Loops in Agents: A Structural Risk via MCP Tools","created":"2026-02-16","cited_by_count":5,"area":"lr"},{"id":"2607.28374","title":"LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger","created":"2026-07-30","cited_by_count":5,"area":"lr"},{"id":"2509.22193","title":"Scale or Reason? A Compute-Equivalent Analysis of Reasoning Distillation","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2509.23962","title":"Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models","created":"2025-09-28","cited_by_count":3,"area":"lr"},{"id":"2510.07761","title":"Test-Time Reasoners Are Strategic Multiple-Choice Test-Takers","created":"2025-10-09","cited_by_count":3,"area":"lr"},{"id":"2602.19281","title":"Limited Reasoning Space: The cage of long-horizon reasoning in LLMs","created":"2026-02-22","cited_by_count":3,"area":"lr"},{"id":"2604.01161","title":"Reasoning Shift: How Context Silently Shortens LLM Reasoning","created":"2026-04-01","cited_by_count":3,"area":"lr"},{"id":"2606.10385","title":"Beyond Absolute Imitation: Anchored Residual Guidance for Privileged On-Policy Distillation","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2602.14917","title":"BFS-PO: Best-First Search for Large Reasoning Models","created":"2026-02-16","cited_by_count":2,"area":"lr"},{"id":"2605.11388","title":"Deep Reasoning in General Purpose Agents via Structured Meta-Cognition","created":"2026-05-12","cited_by_count":2,"area":"lr"},{"id":"2509.24957","title":"Intra-request branch orchestration for efficient LLM reasoning","created":"2025-09-29","cited_by_count":1,"area":"lr"},{"id":"2511.21397","title":"Understanding the Effects of Distractors on Reasoning Vision-Language Models","created":"2025-11-26","cited_by_count":1,"area":"lr"},{"id":"2511.22891","title":"ORION: Teaching Language Models to Reason Efficiently in the Language of Thought","created":"2025-11-28","cited_by_count":1,"area":"lr"},{"id":"2601.23027","title":"Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.14404","title":"Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Traces","created":"2026-02-16","cited_by_count":1,"area":"lr"},{"id":"2603.00207","title":"VisRef: Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal Large Reasoning Models","created":"2026-02-27","cited_by_count":1,"area":"lr"},{"id":"2605.14358","title":"Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces","created":"2026-05-14","cited_by_count":1,"area":"lr"},{"id":"2606.07548","title":"Evaluating Advanced Prompting on Gemini Flash for Multi-Hop Biomedical QA","created":"2026-05-05","cited_by_count":1,"area":"lr"},{"id":"2606.12402","title":"DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?","created":"2026-06-10","cited_by_count":1,"area":"lr"},{"id":"2610.01560","title":"AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Models","created":"2026-10-01","cited_by_count":1,"area":"lr"},{"id":"2512.03272","title":"When Do Symbolic Solvers Enhance Reasoning in Large Language Models?","created":"2025-12-02","cited_by_count":0,"area":"lr"},{"id":"2602.06527","title":"HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction","created":"2026-02-06","cited_by_count":0,"area":"lr"},{"id":"2604.16029","title":"Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning","created":"2026-04-17","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":"2604.26644","title":"When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling","created":"2026-04-29","cited_by_count":0,"area":"lr"},{"id":"2605.22211","title":"CLORE: Content-Level Optimization for Reasoning Efficiency","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2605.28292","title":"CIRF: Tokenizing Chain-of-Thoughts into Reusable Functional Units for Efficient Latent Reasoning in Large Language Models","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.01682","title":"Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning","created":"2026-06-01","cited_by_count":0,"area":"lr"},{"id":"2606.03217","title":"An Asymptotic Theory of Chain-of-Thought in In-Context Learning","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2607.17243","title":"LenGuard-GPC: Length Guarding with Guided-Prompt Consistency for Spatial Reasoning Reinforce Learning","created":"2026-07-19","cited_by_count":0,"area":"lr"},{"id":"2608.13239","title":"Reasoning for Social Audio-Visual Question Answering: Where Do We Stand?","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2609.07103","title":"Revisiting Complete Reasoning Traces for Post-Training","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2609.16055","title":"State of Thought Enables Endogenous Reasoning","created":"2026-09-13","cited_by_count":0,"area":"lr"},{"id":"2610.19890","title":"Frustratingly Easy Majority Voting Using Length Conditioning","created":"2026-10-14","cited_by_count":0,"area":"lr"},{"id":"2610.20328","title":"Argument Graph Uncertainty: Quantifying Uncertainty from the Logical Structure of Reasoning Chains","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}