{"total":42,"rows":[{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2502.04463","title":"Training Language Models to Reason Efficiently","created":"2025-02-06","cited_by_count":247,"area":"lr"},{"id":"2409.05556","title":"SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning","created":"2024-09-09","cited_by_count":94,"area":"lr"},{"id":"2406.02061","title":"Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models","created":"2024-06-04","cited_by_count":68,"area":"lr"},{"id":"2401.05618","title":"The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models","created":"2024-01-11","cited_by_count":63,"area":"lr"},{"id":"2404.04735","title":"MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems","created":"2024-04-06","cited_by_count":41,"area":"lr"},{"id":"2305.14540","title":"LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond","created":"2023-05-23","cited_by_count":38,"area":"lr"},{"id":"2403.14565","title":"A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Science","created":"2024-03-21","cited_by_count":31,"area":"lr"},{"id":"2310.07088","title":"Diversity of Thought Improves Reasoning Abilities of LLMs","created":"2023-10-11","cited_by_count":25,"area":"lr"},{"id":"2405.00622","title":"Causal Evaluation of Language Models","created":"2024-05-01","cited_by_count":18,"area":"lr"},{"id":"2305.07716","title":"Learning to Reason over Scene Graphs: A Case Study of Finetuning GPT-2 into a Robot Language Model for Grounded Task Planning","created":"2023-05-12","cited_by_count":16,"area":"lr"},{"id":"2410.21411","title":"SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization","created":"2024-10-28","cited_by_count":14,"area":"lr"},{"id":"2310.13855","title":"Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing","created":"2023-10-20","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":"2402.01805","title":"Can LLMs perform structured graph reasoning?","created":"2024-02-02","cited_by_count":9,"area":"lr"},{"id":"2308.01727","title":"Local Large Language Models for Complex Structured Medical Tasks","created":"2023-08-03","cited_by_count":7,"area":"lr"},{"id":"2409.00084","title":"Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Models","created":"2024-08-25","cited_by_count":7,"area":"lr"},{"id":"2503.12286","title":"Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical Notes","created":"2025-03-15","cited_by_count":7,"area":"lr"},{"id":"2505.09438","title":"Evaluating GPT- and Reasoning-based Large Language Models on Physics Olympiad Problems: Surpassing Human Performance and Implications for Educational Assessment","created":"2025-05-14","cited_by_count":7,"area":"lr"},{"id":"2501.16884","title":"Irony Detection, Reasoning and Understanding in Zero-shot Learning","created":"2025-01-28","cited_by_count":5,"area":"lr"},{"id":"2505.16686","title":"SPaRC: A Spatial Pathfinding Reasoning Challenge","created":"2025-05-22","cited_by_count":5,"area":"lr"},{"id":"2507.12026","title":"3D-MoRe: Unified Modal-Contextual Reasoning for Embodied Question Answering","created":"2025-07-16","cited_by_count":5,"area":"lr"},{"id":"2604.06699","title":"Adaptive Prompt Structure Factorization: A Framework for Self-Discovering and Optimizing Compositional Prompt Programs","created":"2026-04-08","cited_by_count":5,"area":"lr"},{"id":"2410.11877","title":"A Framework for Collaborating a Large Language Model Tool in Brainstorming for Triggering Creative Thoughts","created":"2024-10-10","cited_by_count":4,"area":"lr"},{"id":"2510.20909","title":"Code-enabled language models can outperform reasoning models on diverse tasks","created":"2025-10-23","cited_by_count":4,"area":"lr"},{"id":"2406.03725","title":"LLMEmbed: Rethinking Lightweight LLM's Genuine Function in Text Classification","created":"2024-06-06","cited_by_count":3,"area":"lr"},{"id":"2405.18073","title":"Towards Dialogues for Joint Human-AI Reasoning and Value Alignment","created":"2024-05-28","cited_by_count":2,"area":"lr"},{"id":"2508.10032","title":"The Cost of Thinking: Increased Jailbreak Risk in Large Language Models","created":"2025-08-09","cited_by_count":2,"area":"lr"},{"id":"2511.17696","title":"Liberating Logic in the Age of AI: Going Beyond Programming with Computational Thinking","created":"2025-11-21","cited_by_count":2,"area":"lr"},{"id":"2309.13165","title":"Large Language Models Are Also Good Prototypical Commonsense Reasoners","created":"2023-09-22","cited_by_count":1,"area":"lr"},{"id":"2404.03891","title":"Can only LLMs do Reasoning?: Potential of Small Language Models in Task Planning","created":"2024-04-05","cited_by_count":1,"area":"lr"},{"id":"2510.09970","title":"Follow My Lead: Logical Fallacy Classification with Knowledge-Augmented LLMs","created":"2025-10-11","cited_by_count":1,"area":"lr"},{"id":"2603.10588","title":"Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning","created":"2026-03-11","cited_by_count":1,"area":"lr"},{"id":"2603.19266","title":"Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion","created":"2026-02-26","cited_by_count":1,"area":"lr"},{"id":"2604.28043","title":"Collaborative Agent Reasoning Engineering (CARE): A Three-Party Design Methodology for Systematically Engineering AI Agents with Subject Matter Experts, Developers, and Helper Agents","created":"2026-04-30","cited_by_count":1,"area":"lr"},{"id":"2405.03010","title":"High Order Reasoning for Time Critical Recommendation in Evidence-based Medicine","created":"2024-05-05","cited_by_count":0,"area":"lr"},{"id":"2506.21609","title":"From Thinking to Output: Chain-of-Thought and Text Generation Characteristics in Reasoning Language Models","created":"2025-06-20","cited_by_count":0,"area":"lr"},{"id":"2511.11769","title":"Socrates-Mol: Self-Oriented Cognitive Reasoning through Autonomous Trial-and-Error with Empirical-Bayesian Screening for Molecules","created":"2025-11-14","cited_by_count":0,"area":"lr"},{"id":"2603.09995","title":"Context Over Compute Human-in-the-Loop Outperforms Iterative Chain-of-Thought Prompting in Interview Answer Quality","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2603.15397","title":"SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration","created":"2026-03-16","cited_by_count":0,"area":"lr"},{"id":"2605.02033","title":"Conventional Commit Classification using Large Language Models and Prompt Engineering","created":"2026-05-03","cited_by_count":0,"area":"lr"},{"id":"2610.18161","title":"Benchmarking Multimodal Large Language Models for Zero-Shot Human-Object Interaction","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}