{"total":203,"rows":[{"id":"2504.16084","title":"TTRL: Test-Time Reinforcement Learning","created":"2025-04-22","cited_by_count":275,"area":"lr"},{"id":"2406.01297","title":"When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs","created":"2024-06-03","cited_by_count":240,"area":null},{"id":"2502.18581","title":"Scalable Best-of-N Selection for Large Language Models via Self-Certainty","created":"2025-02-25","cited_by_count":187,"area":"lr"},{"id":"2407.06023","title":"Distilling System 2 into System 1","created":"2024-07-08","cited_by_count":159,"area":"lr"},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2403.01248","title":"SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code","created":"2024-03-02","cited_by_count":134,"area":"agents"},{"id":"2406.02543","title":"To Believe or Not to Believe Your LLM","created":"2024-06-04","cited_by_count":120,"area":null},{"id":"2402.18563","title":"Approaching Human-Level Forecasting with Language Models","created":"2024-02-28","cited_by_count":107,"area":null},{"id":"2312.09300","title":"Self-Evaluation Improves Selective Generation in Large Language Models","created":"2023-12-14","cited_by_count":76,"area":null},{"id":"2410.07076","title":"MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses","created":"2024-10-09","cited_by_count":72,"area":null},{"id":"2501.19306","title":"SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling","created":"2025-01-31","cited_by_count":54,"area":"lr"},{"id":"2502.00674","title":"Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?","created":"2025-02-02","cited_by_count":54,"area":"lr"},{"id":"2407.14507","title":"Internal Consistency and Self-Feedback in Large Language Models: A Survey","created":"2024-07-19","cited_by_count":50,"area":"lr"},{"id":"2412.14135","title":"Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective","created":"2024-12-18","cited_by_count":50,"area":"lr"},{"id":"2406.12934","title":"Current state of LLM Risks and AI Guardrails","created":"2024-06-16","cited_by_count":46,"area":"safety"},{"id":"2410.01215","title":"From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging","created":"2024-10-02","cited_by_count":46,"area":null},{"id":"2504.01005","title":"When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning","created":"2025-04-01","cited_by_count":42,"area":"lr"},{"id":"2503.18942","title":"Video-T1: Test-Time Scaling for Video Generation","created":"2025-03-24","cited_by_count":40,"area":"lr"},{"id":"2402.06544","title":"Calibrating Long-form Generations from Large Language Models","created":"2024-02-09","cited_by_count":32,"area":null},{"id":"2312.04455","title":"Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use","created":"2023-12-07","cited_by_count":27,"area":null},{"id":"2503.04104","title":"LLMs Can Generate a Better Answer by Aggregating Their Own Responses","created":"2025-03-06","cited_by_count":27,"area":null},{"id":"2404.09127","title":"Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation","created":"2024-04-14","cited_by_count":26,"area":"agents"},{"id":"2510.01499","title":"Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information","created":"2025-10-01","cited_by_count":26,"area":"lr"},{"id":"2402.13212","title":"Soft Self-Consistency Improves Language Model Agents","created":"2024-02-20","cited_by_count":25,"area":"lr"},{"id":"2408.08656","title":"LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs","created":"2024-08-16","cited_by_count":25,"area":null},{"id":"2409.00089","title":"Watermarking Techniques for Large Language Models: A Survey","created":"2024-08-26","cited_by_count":23,"area":"safety"},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"id":"2408.00397","title":"In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translation","created":"2024-08-01","cited_by_count":22,"area":null},{"id":"2407.02056","title":"Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation","created":"2024-07-02","cited_by_count":21,"area":"lr"},{"id":"2402.19475","title":"The Counterfeit Conundrum: Can Code Language Models Grasp the Nuances of Their Incorrect Generations?","created":"2024-02-29","cited_by_count":20,"area":null},{"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":"2402.08733","title":"Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs","created":"2024-02-13","cited_by_count":19,"area":null},{"id":"2410.02902","title":"Better Instruction-Following Through Minimum Bayes Risk","created":"2024-10-03","cited_by_count":19,"area":null},{"id":"2408.06303","title":"Long-Form Answers to Visual Questions from Blind and Low Vision People","created":"2024-08-12","cited_by_count":18,"area":"mllm"},{"id":"2502.00511","title":"Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning","created":"2025-02-01","cited_by_count":18,"area":"lr"},{"id":"2502.14727","title":"WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models","created":"2025-02-20","cited_by_count":18,"area":"rag"},{"id":"2602.09341","title":"Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge","created":"2026-02-10","cited_by_count":18,"area":"lr"},{"id":"2403.05307","title":"Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents","created":"2024-03-08","cited_by_count":17,"area":"agents"},{"id":"2511.09092","title":"OR-R1: Automating Modeling and Solving of Operations Research Optimization Problem via Test-Time Reinforcement Learning","created":"2025-11-12","cited_by_count":17,"area":"lr"},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2402.06625","title":"Understanding the Effects of Iterative Prompting on Truthfulness","created":"2024-02-09","cited_by_count":14,"area":null},{"id":"2411.00492","title":"Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models","created":"2024-11-01","cited_by_count":14,"area":null},{"id":"2505.17126","title":"Conformal Language Model Reasoning with Coherent Factuality","created":"2025-05-21","cited_by_count":14,"area":"lr"},{"id":"2510.15444","title":"A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning","created":"2025-10-17","cited_by_count":14,"area":"lr"},{"id":"2503.13288","title":"$\\phi$-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation","created":"2025-03-17","cited_by_count":13,"area":"lr"},{"id":"2504.09440","title":"Enhancing Mathematical Reasoning in Large Language Models with Self-Consistency-Based Hallucination Detection","created":"2025-04-13","cited_by_count":13,"area":"lr"},{"id":"2404.09129","title":"When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language Models","created":"2024-04-14","cited_by_count":12,"area":"lr"},{"id":"2507.08960","title":"How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs","created":"2025-07-11","cited_by_count":12,"area":"lr"},{"id":"2508.16861","title":"Learning from Diverse Reasoning Paths with Routing and Collaboration","created":"2025-08-23","cited_by_count":12,"area":"lr"},{"id":"2511.17938","title":"SPINE: Token-Selective Test-Time Reinforcement Learning with Entropy-Band Regularization","created":"2025-11-22","cited_by_count":12,"area":"lr"},{"id":"2512.03503","title":"Understanding LLM Reasoning for Abstractive Summarization","created":"2025-12-03","cited_by_count":12,"area":"lr"},{"id":"2604.23626","title":"GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs","created":"2026-04-26","cited_by_count":12,"area":"agents"},{"id":"2406.05365","title":"CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation","created":"2024-06-08","cited_by_count":11,"area":null},{"id":"2502.19830","title":"Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation","created":"2025-02-27","cited_by_count":11,"area":"lr"},{"id":"2405.13131","title":"Atomic Self-Consistency for Better Long Form Generations","created":"2024-05-21","cited_by_count":10,"area":"lr"},{"id":"2410.04778","title":"MM-R$^3$: On (In-)Consistency of Vision-Language Models (VLMs)","created":"2024-10-07","cited_by_count":10,"area":"mllm"},{"id":"2411.14461","title":"Towards Next-Generation Medical Agent: How o1 is Reshaping Decision-Making in Medical Scenarios","created":"2024-11-16","cited_by_count":10,"area":"agents"},{"id":"2507.06829","title":"Adaptive Termination for Multi-round Parallel Reasoning: An Universal Semantic Entropy-Guided Framework","created":"2025-07-09","cited_by_count":10,"area":"lr"},{"id":"2508.05188","title":"Incident Response Planning Using a Lightweight Large Language Model with Reduced Hallucination","created":"2025-08-07","cited_by_count":10,"area":null},{"id":"2508.21787","title":"PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains","created":"2025-08-29","cited_by_count":10,"area":"lr"},{"id":"2510.13855","title":"Harnessing Consistency for Robust Test-Time LLM Ensemble","created":"2025-10-12","cited_by_count":10,"area":null},{"id":"2510.26277","title":"Do LLMs Signal When They're Right? Evidence from Neuron Agreement","created":"2025-10-30","cited_by_count":10,"area":"lr"},{"id":"2501.09349","title":"ChartInsighter: An Approach for Mitigating Hallucination in Time-series Chart Summary Generation with A Benchmark Dataset","created":"2025-01-16","cited_by_count":9,"area":null},{"id":"2507.20187","title":"Diversity-Enhanced Reasoning for Subjective Questions","created":"2025-07-27","cited_by_count":9,"area":"lr"},{"id":"2509.13761","title":"THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning","created":"2025-09-17","cited_by_count":9,"area":"lr"},{"id":"2511.12309","title":"Optimal Self-Consistency for Efficient Reasoning with Large Language Models","created":"2025-11-15","cited_by_count":9,"area":"lr"},{"id":"2410.01556","title":"Integrative Decoding: Improve Factuality via Implicit Self-consistency","created":"2024-10-02","cited_by_count":8,"area":"lr"},{"id":"2510.20812","title":"Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via Speculation","created":"2025-10-23","cited_by_count":8,"area":"lr"},{"id":"2512.07843","title":"ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models","created":"2025-11-24","cited_by_count":8,"area":"lr"},{"id":"2603.18940","title":"Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thought","created":"2026-03-19","cited_by_count":8,"area":"lr"},{"id":"2402.15631","title":"Fine-Grained Self-Endorsement Improves Factuality and Reasoning","created":"2024-02-23","cited_by_count":7,"area":"lr"},{"id":"2404.16478","title":"Evaluating Consistency and Reasoning Capabilities of Large Language Models","created":"2024-04-25","cited_by_count":7,"area":"lr"},{"id":"2501.01668","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","created":"2025-01-03","cited_by_count":7,"area":"lr"},{"id":"2504.20084","title":"AI Awareness","created":"2025-04-25","cited_by_count":7,"area":null},{"id":"2509.15172","title":"Self-Improvement of Language Models by Post-Training on Multi-Agent Debate","created":"2025-09-18","cited_by_count":7,"area":"agents"},{"id":"2510.01143","title":"Generalized Parallel Scaling with Interdependent Generations","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2510.05077","title":"Slm-mux: Orchestrating small language models for reasoning","created":"2025-10-06","cited_by_count":6,"area":"lr"},{"id":"2512.02874","title":"Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning","created":"2025-12-02","cited_by_count":6,"area":"lr"},{"id":"2512.04558","title":"On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inference","created":"2025-12-04","cited_by_count":6,"area":"lr"},{"id":"2608.04001","title":"Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility","created":"2026-08-04","cited_by_count":6,"area":"lr"},{"id":"2406.14629","title":"Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study","created":"2024-06-20","cited_by_count":5,"area":"lr"},{"id":"2410.00689","title":"Multimodal Auto Validation For Self-Refinement in Web Agents","created":"2024-10-01","cited_by_count":5,"area":"agents"},{"id":"2502.17321","title":"Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agents","created":"2025-02-24","cited_by_count":5,"area":null},{"id":"2502.18473","title":"Disproving Program Equivalence with LLMs","created":"2025-02-05","cited_by_count":5,"area":null},{"id":"2503.05330","title":"Speculative Decoding for Multi-Sample Inference","created":"2025-03-07","cited_by_count":5,"area":"lr"},{"id":"2506.03857","title":"Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation","created":"2025-06-04","cited_by_count":5,"area":"distill"},{"id":"2506.18781","title":"Existing LLMs Are Not Self-Consistent For Simple Tasks","created":"2025-06-23","cited_by_count":5,"area":"lr"},{"id":"2510.22228","title":"When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs","created":"2025-10-25","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":"2602.19715","title":"Pixels Don't Lie (But Your Detector Might): Bootstrapping MLLM-as-a-Judge for Trustworthy Deepfake Detection and Reasoning Supervision","created":"2026-02-23","cited_by_count":5,"area":null},{"id":"2406.08842","title":"ContraSolver: Self-Alignment of Language Models by Resolving Internal Preference Contradictions","created":"2024-06-13","cited_by_count":4,"area":"alignment"},{"id":"2502.16395","title":"AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science","created":"2025-02-23","cited_by_count":4,"area":null},{"id":"2503.03106","title":"Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation","created":"2025-03-05","cited_by_count":4,"area":null},{"id":"2504.18346","title":"Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review","created":"2025-04-25","cited_by_count":4,"area":null},{"id":"2506.17251","title":"Training-free LLM Verification via Recycling Few-shot Examples","created":"2025-06-08","cited_by_count":4,"area":"lr"},{"id":"2509.17238","title":"MoEs Are Stronger than You Think: Hyper-Parallel Inference Scaling with RoE","created":"2025-09-21","cited_by_count":4,"area":"lr"},{"id":"2509.21451","title":"VideoJudge: Bootstrapping Enables Scalable Supervision of MLLM-as-a-Judge for Video Understanding","created":"2025-09-25","cited_by_count":4,"area":"synth"},{"id":"2510.05825","title":"Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling","created":"2025-10-07","cited_by_count":4,"area":"lr"},{"id":"2511.04234","title":"Reusing Pre-Training Data at Test Time is a Compute Multiplier","created":"2025-11-06","cited_by_count":4,"area":null}],"next_cursor":"100"}