{"total":57,"rows":[{"id":"2506.10947","title":"Spurious Rewards: Rethinking Training Signals in RLVR","created":"2025-06-12","cited_by_count":209,"area":"lr"},{"id":"2406.00922","title":"MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning","created":"2024-06-03","cited_by_count":154,"area":"lr"},{"id":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111,"area":"lr"},{"id":"2411.18478","title":"Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS","created":"2024-11-27","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":"2509.01790","title":"Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs","created":"2025-09-01","cited_by_count":30,"area":"lr"},{"id":"2410.19599","title":"Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina","created":"2024-10-25","cited_by_count":29,"area":"lr"},{"id":"2508.04826","title":"Persistent Instability in LLM's Personality Measurements: Effects of Scale, Reasoning, and Conversation History","created":"2025-08-06","cited_by_count":26,"area":"lr"},{"id":"2404.03134","title":"Robust Pronoun Fidelity with English LLMs: Are they Reasoning, Repeating, or Just Biased?","created":"2024-04-04","cited_by_count":17,"area":"lr"},{"id":"2403.02246","title":"PHAnToM: Persona-based Prompting Has An Effect on Theory-of-Mind Reasoning in Large Language Models","created":"2024-03-04","cited_by_count":16,"area":"lr"},{"id":"2508.21422","title":"Automatic Reviewers Fail to Detect Faulty Reasoning in Research Papers: A New Counterfactual Evaluation Framework","created":"2025-08-29","cited_by_count":11,"area":"lr"},{"id":"2604.02547","title":"Beyond Resolution Rates: Behavioral Drivers of Coding Agent Success and Failure","created":"2026-04-02","cited_by_count":11,"area":"lr"},{"id":"2402.11541","title":"Large Language Models Can Better Understand Knowledge Graphs Than We Thought","created":"2024-02-18","cited_by_count":10,"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":"2609.31142","title":"JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models","created":"2026-09-25","cited_by_count":10,"area":"lr"},{"id":"2505.14412","title":"PRL: Prompts from Reinforcement Learning","created":"2025-05-20","cited_by_count":9,"area":"lr"},{"id":"2603.00131","title":"Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems","created":"2026-02-23","cited_by_count":9,"area":"lr"},{"id":"2407.17125","title":"To Know or Not To Know? Analyzing Self-Consistency of Large Language Models under Ambiguity","created":"2024-07-24","cited_by_count":8,"area":"lr"},{"id":"2503.19599","title":"HoarePrompt: Structural Reasoning About Program Correctness in Natural Language","created":"2025-03-25","cited_by_count":7,"area":"lr"},{"id":"2506.03923","title":"More or Less Wrong: A Benchmark for Directional Bias in LLM Comparative Reasoning","created":"2025-06-04","cited_by_count":7,"area":"lr"},{"id":"2512.23631","title":"BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimization","created":"2025-12-29","cited_by_count":7,"area":"lr"},{"id":"2605.18891","title":"Auditing Reasoning-Trace Memorization Claims after Unlearning with Head-Conditioned Canaries","created":"2026-05-17","cited_by_count":7,"area":"lr"},{"id":"2409.15551","title":"Revise, Reason, and Recognize: LLM-Based Emotion Recognition via Emotion-Specific Prompts and ASR Error Correction","created":"2024-09-23","cited_by_count":5,"area":"lr"},{"id":"2506.21590","title":"Representation Consistency for Accurate and Coherent LLM Answer Aggregation","created":"2025-06-18","cited_by_count":5,"area":"lr"},{"id":"2601.07525","title":"Thinking Before Constraining: A Unified Decoding Framework for Large Language Models","created":"2026-01-12","cited_by_count":5,"area":"lr"},{"id":"2506.10415","title":"Burn After Reading: Do Multimodal Large Language Models Truly Capture Order of Events in Image Sequences?","created":"2025-06-12","cited_by_count":4,"area":"lr"},{"id":"2510.04141","title":"The Artificial Intelligence Cognitive Examination: A Survey on the Evolution of Multimodal Evaluation from Recognition to Reasoning","created":"2025-10-05","cited_by_count":4,"area":"lr"},{"id":"2510.14773","title":"Finding Answers in Thought Matters: Revisiting Evaluation on Large Language Models with Reasoning","created":"2025-10-16","cited_by_count":4,"area":"lr"},{"id":"2404.15206","title":"Does Instruction Tuning Make LLMs More Consistent?","created":"2024-04-23","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":"2602.00723","title":"Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity","created":"2026-01-31","cited_by_count":2,"area":"lr"},{"id":"2603.09957","title":"Think Before You Lie: How Reasoning Leads to Honesty","created":"2026-03-10","cited_by_count":2,"area":"lr"},{"id":"2605.07053","title":"GSM-SEM: Benchmark and Framework for Generating Semantically Variant Augmentations","created":"2026-05-08","cited_by_count":2,"area":"lr"},{"id":"2609.04518","title":"Multi-Harness Reinforcement Learning for Coding Agents: Training Gains and Harness Dependence","created":"2026-09-03","cited_by_count":2,"area":"lr"},{"id":"2511.22176","title":"Focused Chain-of-Thought: Efficient LLM Reasoning via Structured Input Information","created":"2025-11-27","cited_by_count":1,"area":"lr"},{"id":"2602.06081","title":"Communication Enhances LLMs' Stability in Strategic Thinking","created":"2026-02-04","cited_by_count":1,"area":"lr"},{"id":"2602.10282","title":"Linear-LLM-SCM: Benchmarking LLMs for Coefficient Elicitation in Linear-Gaussian Causal Models","created":"2026-02-10","cited_by_count":1,"area":"lr"},{"id":"2604.07035","title":"Unified Deployment-Aware Evaluation of Open Reasoning Language Models","created":"2026-04-08","cited_by_count":1,"area":"lr"},{"id":"2604.07801","title":"TEMPER: Testing Emotional Perturbation in Quantitative Reasoning","created":"2026-04-09","cited_by_count":1,"area":"lr"},{"id":"2606.18327","title":"Self-CTRL: Self-Consistency Training with Reinforcement Learning","created":"2026-06-16","cited_by_count":1,"area":"lr"},{"id":"2609.36931","title":"Dating the Model: Hidden Dates in System Prompts Affect LLM Evaluation","created":"2026-09-29","cited_by_count":1,"area":"lr"},{"id":"2508.06503","title":"Understanding Human Limits in Pattern Recognition: A Computational Model of Sequential Reasoning in Rock, Paper, Scissors","created":"2025-07-25","cited_by_count":0,"area":"lr"},{"id":"2508.19271","title":"Rethinking Reasoning in LLMs: Neuro-Symbolic Local RetoMaton Beyond ICL and CoT","created":"2025-08-22","cited_by_count":0,"area":"lr"},{"id":"2602.10816","title":"Beyond Confidence: The Rhythms of Reasoning in Generative Models","created":"2026-02-11","cited_by_count":0,"area":"lr"},{"id":"2603.22730","title":"How Utilitarian Are OpenAI's Models Really? Replicating and Reinterpreting Pfeffer, Kr\\\"ugel, and Uhl (2025)","created":"2026-03-24","cited_by_count":0,"area":"lr"},{"id":"2605.28700","title":"The Importance of Being Statistically Earnest: A Critical Re-evaluation of GSM-Symbolic","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.27103","title":"The Riddle Riddle: Testing Flexible Reasoning in Large Language Models and Humans","created":"2026-06-25","cited_by_count":0,"area":"lr"},{"id":"2606.29639","title":"Two-Stage Prompt Optimization for Few-Shot Relation Extraction: From Reasoning-Guided Search to Gradient-Guided Refinement","created":"2026-06-28","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":"2607.24471","title":"Grounding latent algorithm routing in transformer reasoning","created":"2026-07-27","cited_by_count":0,"area":"lr"},{"id":"2608.11047","title":"V-FiLLM: Verified Financial LLM Reasoning Benchmark","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.18631","title":"Preference Reasoning under Indeterminacy in Large Language Models","created":"2026-08-19","cited_by_count":0,"area":"lr"},{"id":"2608.22140","title":"Lexical Perturbations Disrupt LLM Reasoning: An Empirical Study of Attention Diversion","created":"2026-08-22","cited_by_count":0,"area":"lr"},{"id":"2609.01867","title":"Thinking effort aligns between humans and reasoning models in abductive reasoning","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2609.04543","title":"From Answers to Interpretations: Rethinking Ambiguity-Induced Aleatoric Uncertainty Estimation in LLMs","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2609.12265","title":"GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs","created":"2026-09-10","cited_by_count":0,"area":"lr"},{"id":"2610.00437","title":"JevSpawn: Adaptive Agentic Inference through Compositional Action Spaces","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}