{"total":41,"rows":[{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95,"area":"lr"},{"id":"2504.03846","title":"Do LLM Evaluators Prefer Themselves for a Reason?","created":"2025-04-04","cited_by_count":38,"area":"lr"},{"id":"2410.06458","title":"LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints","created":"2024-10-09","cited_by_count":35,"area":"lr"},{"id":"2407.13647","title":"Weak-to-Strong Reasoning","created":"2024-07-18","cited_by_count":33,"area":"lr"},{"id":"2503.15707","title":"Safety Aware Task Planning via Large Language Models in Robotics","created":"2025-03-19","cited_by_count":24,"area":"lr"},{"id":"2409.04168","title":"From Calculation to Adjudication: Examining LLM judges on Mathematical Reasoning Tasks","created":"2024-09-06","cited_by_count":22,"area":"lr"},{"id":"2602.02639","title":"A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior","created":"2026-02-02","cited_by_count":13,"area":"lr"},{"id":"2506.06877","title":"Right Is Not Enough: The Pitfalls of Outcome Supervision in Training LLMs for Math Reasoning","created":"2025-06-07","cited_by_count":10,"area":"lr"},{"id":"2603.20215","title":"Multi-Agent Debate with Memory Masking","created":"2026-03-03","cited_by_count":10,"area":"lr"},{"id":"2508.18255","title":"Hermes 4 Technical Report","created":"2025-08-25","cited_by_count":8,"area":"lr"},{"id":"2603.21728","title":"EvoIdeator: Evolving Scientific Ideas through Checklist-Grounded Reinforcement Learning","created":"2026-03-23","cited_by_count":6,"area":"lr"},{"id":"2601.16130","title":"Replicating Human Motivated Reasoning Studies with LLMs","created":"2026-01-22","cited_by_count":5,"area":"lr"},{"id":"2506.05766","title":"BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions","created":"2025-06-06","cited_by_count":4,"area":"lr"},{"id":"2505.16849","title":"Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walks","created":"2025-05-22","cited_by_count":2,"area":"lr"},{"id":"2507.18442","title":"AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Data","created":"2025-07-24","cited_by_count":2,"area":"lr"},{"id":"2602.00723","title":"Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity","created":"2026-01-31","cited_by_count":2,"area":"lr"},{"id":"2606.29689","title":"Can MLLMs Critique Like Humans? Evaluating Open-Ended Aesthetic Reasoning in Multimodal Large Language Models","created":"2026-06-29","cited_by_count":2,"area":"lr"},{"id":"2607.02436","title":"Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study","created":"2026-07-02","cited_by_count":2,"area":"lr"},{"id":"2607.08066","title":"Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2502.03253","title":"How do Humans and Language Models Reason About Creativity? A Comparative Analysis","created":"2025-02-05","cited_by_count":1,"area":"lr"},{"id":"2510.05135","title":"Curiosity-Driven LLM-as-a-judge for Personalized Creative Judgment","created":"2025-10-01","cited_by_count":1,"area":"lr"},{"id":"2601.19673","title":"A Benchmark for Audio Reasoning Capabilities of Multimodal Large Language Models","created":"2026-01-27","cited_by_count":1,"area":"lr"},{"id":"2606.16149","title":"Teaching agentic AI to generalize expert diagnostic reasoning in rare diseases","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"id":"2606.16545","title":"Can LLM Coding Agents Reason About Time Series?","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"id":"2607.09438","title":"Test-Time Scaling for Small VLMs on Multilingual Visual MCQ","created":"2026-07-10","cited_by_count":1,"area":"lr"},{"id":"2412.11763","title":"QUENCH: Measuring the gap between Indic and Non-Indic Contextual General Reasoning in LLMs","created":"2024-12-16","cited_by_count":0,"area":"lr"},{"id":"2512.14465","title":"Context-Picker: Dynamic context selection using multi-stage reinforcement learning","created":"2025-12-16","cited_by_count":0,"area":"lr"},{"id":"2604.05134","title":"How Reasoning Evolves from Post-Training Data: An Empirical Study Using Chess","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2605.29076","title":"Structured Prompt Optimization Meets Reinforcement Learning for Global and Local Interpretability over Complex Text","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.29672","title":"How LLMs See Creativity: Zero-Shot Scoring of Visual Creativity with Interpretable Reasoning","created":"2026-06-29","cited_by_count":0,"area":"lr"},{"id":"2606.30653","title":"The Consistency Dilemma in LLMs: Generator-Evaluator Agreement and Vulnerability to Mistakes","created":"2026-06-16","cited_by_count":0,"area":"lr"},{"id":"2607.19678","title":"Reference-Free Evaluation of Reasoning in Open-Ended Question Answering","created":"2026-07-22","cited_by_count":0,"area":"lr"},{"id":"2608.07813","title":"When the Judge Should Not Decide: Evidence-Locked, Non-Compensatory Selection Bounds LLM-Judge Failure in Reasoning Pipelines","created":"2026-08-07","cited_by_count":0,"area":"lr"},{"id":"2608.09591","title":"FactorDrive: Adaptive Multi-Step Reasoning Driven by Planning-Critical Factors for End-to-End Autonomous Driving","created":"2026-08-10","cited_by_count":0,"area":"lr"},{"id":"2608.09706","title":"Test-Time Scaling for CAD Generation via Verifier-Free Consensus Selection","created":"2026-08-10","cited_by_count":0,"area":"lr"},{"id":"2608.12781","title":"Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2609.12822","title":"Scaling Clinical Judgment to Evaluate Medical AI","created":"2026-09-11","cited_by_count":0,"area":"lr"},{"id":"2609.22194","title":"A Pinch of SFT, A Dash of RL: When Reinforcement Learning Helps Long-Horizon Advertising Agents","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2610.08966","title":"Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.12601","title":"Reflective Prompt Optimization of a Deep-Research Agent: A Topic-Disjoint, Multi-Seed Protocol for Measuring Transferable Gains and Prompt-Level Overfitting","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.19176","title":"Learning from Self-Generated Responses: Reliability--Uncertainty Self-Distillation for Reasoning","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}