{"total":97,"rows":[{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894,"area":"lr"},{"id":"2210.01240","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","created":"2022-10-03","cited_by_count":337,"area":"lr"},{"id":"2205.09712","title":"Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning","created":"2022-05-19","cited_by_count":334,"area":"lr"},{"id":"2406.10149","title":"BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack","created":"2024-06-14","cited_by_count":215,"area":"lr"},{"id":"2310.16049","title":"MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning","created":"2023-10-24","cited_by_count":201,"area":"lr"},{"id":"2205.03401","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","created":"2022-05-06","cited_by_count":169,"area":"lr"},{"id":"2305.14763","title":"Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models","created":"2023-05-24","cited_by_count":163,"area":"lr"},{"id":"2402.14848","title":"Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models","created":"2024-02-19","cited_by_count":152,"area":"lr"},{"id":"2502.19187","title":"BIG-Bench Extra Hard","created":"2025-02-26","cited_by_count":125,"area":"lr"},{"id":"2204.05660","title":"NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks","created":"2022-04-12","cited_by_count":112,"area":"lr"},{"id":"2410.19258","title":"Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning","created":"2024-10-25","cited_by_count":97,"area":"lr"},{"id":"2204.08292","title":"StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Texts","created":"2022-04-18","cited_by_count":68,"area":"lr"},{"id":"2404.03622","title":"Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models","created":"2024-04-04","cited_by_count":66,"area":"lr"},{"id":"2306.09841","title":"Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond","created":"2023-06-16","cited_by_count":65,"area":"lr"},{"id":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"area":"lr"},{"id":"2307.07696","title":"Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text","created":"2023-07-15","cited_by_count":59,"area":"lr"},{"id":"2402.06044","title":"OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models","created":"2024-02-08","cited_by_count":54,"area":"lr"},{"id":"2406.02537","title":"TopViewRS: Vision-Language Models as Top-View Spatial Reasoners","created":"2024-06-04","cited_by_count":49,"area":"lr"},{"id":"2306.07934","title":"BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information","created":"2023-06-13","cited_by_count":44,"area":"lr"},{"id":"2201.12382","title":"Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices","created":"2022-01-28","cited_by_count":37,"area":"lr"},{"id":"2310.00836","title":"Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models","created":"2023-10-02","cited_by_count":35,"area":"lr"},{"id":"2210.16952","title":"Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoning","created":"2022-10-30","cited_by_count":34,"area":"lr"},{"id":"2305.12477","title":"GPT-3.5, GPT-4, or BARD? Evaluating LLMs Reasoning Ability in Zero-Shot Setting and Performance Boosting Through Prompts","created":"2023-05-21","cited_by_count":34,"area":"lr"},{"id":"2405.20535","title":"Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning","created":"2024-05-30","cited_by_count":31,"area":"lr"},{"id":"2305.00833","title":"Learning to Reason and Memorize with Self-Notes","created":"2023-05-01","cited_by_count":30,"area":"lr"},{"id":"2203.10261","title":"FaiRR: Faithful and Robust Deductive Reasoning over Natural Language","created":"2022-03-19","cited_by_count":29,"area":"lr"},{"id":"2411.12498","title":"Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus","created":"2024-11-19","cited_by_count":29,"area":"lr"},{"id":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28,"area":"lr"},{"id":"2401.03991","title":"Advancing Spatial Reasoning in Large Language Models: An In-Depth Evaluation and Enhancement Using the StepGame Benchmark","created":"2024-01-08","cited_by_count":27,"area":"lr"},{"id":"2301.10896","title":"Causal Reasoning of Entities and Events in Procedural Texts","created":"2023-01-26","cited_by_count":23,"area":"lr"},{"id":"2511.15722","title":"Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods","created":"2025-11-14","cited_by_count":23,"area":"lr"},{"id":"2502.07827","title":"Implicit Language Models are RNNs: Balancing Parallelization and Expressivity","created":"2025-02-10","cited_by_count":22,"area":"lr"},{"id":"2505.15801","title":"VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models","created":"2025-05-21","cited_by_count":20,"area":"lr"},{"id":"2308.07336","title":"Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic","created":"2023-08-11","cited_by_count":18,"area":"lr"},{"id":"2212.08286","title":"ALERT: Adapting Language Models to Reasoning Tasks","created":"2022-12-16","cited_by_count":17,"area":"lr"},{"id":"2405.15064","title":"Reframing Spatial Reasoning Evaluation in Language Models: A Real-World Simulation Benchmark for Qualitative Reasoning","created":"2024-05-23","cited_by_count":17,"area":"lr"},{"id":"2207.14000","title":"Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation","created":"2022-07-28","cited_by_count":15,"area":"lr"},{"id":"2410.09207","title":"P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains","created":"2024-10-11","cited_by_count":15,"area":"lr"},{"id":"2502.20377","title":"PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation","created":"2025-02-27","cited_by_count":14,"area":"lr"},{"id":"2210.17517","title":"Lila: A Unified Benchmark for Mathematical Reasoning","created":"2022-10-31","cited_by_count":13,"area":"lr"},{"id":"2410.08126","title":"Mars: Situated Inductive Reasoning in an Open-World Environment","created":"2024-10-10","cited_by_count":11,"area":"lr"},{"id":"2203.10610","title":"Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue Systems","created":"2022-03-20","cited_by_count":10,"area":"lr"},{"id":"2503.16779","title":"Chain-of-Tools: Utilizing Massive Unseen Tools in the CoT Reasoning of Frozen Language Models","created":"2025-03-21","cited_by_count":10,"area":"lr"},{"id":"2205.10714","title":"Interpretable Proof Generation via Iterative Backward Reasoning","created":"2022-05-22","cited_by_count":9,"area":"lr"},{"id":"2306.04031","title":"Certified Deductive Reasoning with Language Models","created":"2023-06-06","cited_by_count":8,"area":"lr"},{"id":"2409.12437","title":"Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data","created":"2024-09-19","cited_by_count":8,"area":"lr"},{"id":"2505.13792","title":"Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation","created":"2025-05-20","cited_by_count":8,"area":"lr"},{"id":"2507.20395","title":"MazeEval: A Benchmark for Testing Sequential Decision-Making in Language Models","created":"2025-07-27","cited_by_count":8,"area":"lr"},{"id":"2211.05392","title":"EvEntS ReaLM: Event Reasoning of Entity States via Language Models","created":"2022-11-10","cited_by_count":7,"area":"lr"},{"id":"2305.13179","title":"Teaching Probabilistic Logical Reasoning to Transformers","created":"2023-05-22","cited_by_count":7,"area":"lr"},{"id":"2509.24096","title":"GEAR: A General Evaluation Framework for Abductive Reasoning","created":"2025-09-28","cited_by_count":6,"area":"lr"},{"id":"2202.04161","title":"Logical Reasoning for Task Oriented Dialogue Systems","created":"2022-02-08","cited_by_count":5,"area":"lr"},{"id":"2406.04566","title":"SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models","created":"2024-06-07","cited_by_count":5,"area":"lr"},{"id":"2410.06735","title":"Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance?","created":"2024-10-09","cited_by_count":5,"area":"lr"},{"id":"2505.21935","title":"From Reasoning to Learning: A Survey on Hypothesis Discovery and Rule Learning with Large Language Models","created":"2025-05-28","cited_by_count":5,"area":"lr"},{"id":"2406.13828","title":"Neuro-symbolic Training for Reasoning over Spatial Language","created":"2024-06-19","cited_by_count":4,"area":"lr"},{"id":"2508.12425","title":"Non-Interactive Symbolic-Aided Chain-of-Thought for Logical Reasoning","created":"2025-08-17","cited_by_count":4,"area":"lr"},{"id":"2509.16590","title":"Question Answering with LLMs and Learning from Answer Sets","created":"2025-09-20","cited_by_count":4,"area":"lr"},{"id":"2310.12557","title":"DepWiGNN: A Depth-wise Graph Neural Network for Multi-hop Spatial Reasoning in Text","created":"2023-10-19","cited_by_count":3,"area":"lr"},{"id":"2502.02007","title":"Reasoning Bias of Next Token Prediction Training","created":"2025-02-04","cited_by_count":3,"area":"lr"},{"id":"2502.17169","title":"Logic Haystacks: Probing LLMs Long-Context Logical Reasoning (Without Easily Identifiable Unrelated Padding)","created":"2025-02-24","cited_by_count":3,"area":"lr"},{"id":"2503.06218","title":"SCoRE: Benchmarking Long-Chain Reasoning in Commonsense Scenarios","created":"2025-03-08","cited_by_count":3,"area":"lr"},{"id":"2601.09805","title":"Improving Chain-of-Thought for Logical Reasoning via Attention-Aware Intervention","created":"2026-01-14","cited_by_count":3,"area":"lr"},{"id":"2603.18886","title":"Reasoning over mathematical objects: on-policy reward modeling and test time aggregation","created":"2026-03-19","cited_by_count":3,"area":"lr"},{"id":"2301.02983","title":"Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text","created":"2023-01-08","cited_by_count":2,"area":"lr"},{"id":"2311.06736","title":"Are LLMs Rigorous Logical Reasoners? Empowering Natural Language Proof Generation by Stepwise Decoding with Contrastive Learning","created":"2023-11-12","cited_by_count":2,"area":"lr"},{"id":"2311.07759","title":"Enabling High-Level Machine Reasoning with Cognitive Neuro-Symbolic Systems","created":"2023-11-13","cited_by_count":2,"area":"lr"},{"id":"2503.07903","title":"Can Memory-Augmented Language Models Generalize on Reasoning-in-a-Haystack Tasks?","created":"2025-03-10","cited_by_count":2,"area":"lr"},{"id":"2505.23126","title":"PBEBench: A Multi-Step Programming by Examples Reasoning Benchmark inspired by Historical Linguistics","created":"2025-05-29","cited_by_count":2,"area":"lr"},{"id":"2509.16866","title":"seqBench: A Tunable Benchmark to Quantify Sequential Reasoning Limits of LLMs","created":"2025-09-21","cited_by_count":2,"area":"lr"},{"id":"2603.03002","title":"SpatialText: A Pure-Text Cognitive Benchmark for Spatial Understanding in Large Language Models","created":"2026-03-03","cited_by_count":2,"area":"lr"},{"id":"2210.06316","title":"Non-Axiomatic Term Logic: A Computational Theory of Cognitive Symbolic Reasoning","created":"2022-10-12","cited_by_count":1,"area":"lr"},{"id":"2305.00061","title":"Explainable Verbal Reasoner Plus (EVR+): A Natural Language Reasoning Framework that Supports Diverse Compositional Reasoning","created":"2023-04-28","cited_by_count":1,"area":"lr"},{"id":"2309.07974","title":"A Data Source for Reasoning Embodied Agents","created":"2023-09-14","cited_by_count":1,"area":"lr"},{"id":"2410.13666","title":"VL-GLUE: A Suite of Fundamental yet Challenging Visuo-Linguistic Reasoning Tasks","created":"2024-10-17","cited_by_count":1,"area":"lr"},{"id":"2412.08317","title":"Large Language Models Still Face Challenges in Multi-Hop Reasoning with External Knowledge","created":"2024-12-11","cited_by_count":1,"area":"lr"},{"id":"2507.12059","title":"Evaluating the Ability of Large Language Models to Reason about Cardinal Directions, Revisited","created":"2025-07-16","cited_by_count":1,"area":"lr"},{"id":"2507.15707","title":"Is Large Language Model Performance on Reasoning Tasks Impacted by Different Ways Questions Are Asked?","created":"2025-07-21","cited_by_count":1,"area":"lr"},{"id":"2602.02842","title":"Chain of Simulation: A Dual-Mode Reasoning Framework for Large Language Models with Dynamic Problem Routing","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2604.09338","title":"Mind the Gap Between Spatial Reasoning and Acting! Step-by-Step Evaluation of Agents With Spatial-Gym","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2605.18380","title":"QSTRBench: a New Benchmark to Evaluate the Ability of Language Models to Reason with Qualitative Spatial and Temporal Calculi","created":"2026-05-18","cited_by_count":1,"area":"lr"},{"id":"2606.23687","title":"Randomized YaRN Improves Length Generalization for Long-Context Reasoning","created":"2026-06-22","cited_by_count":1,"area":"lr"},{"id":"2211.13930","title":"TRAC: A Textual Benchmark for Reasoning about Actions and Change","created":"2022-11-25","cited_by_count":0,"area":"lr"},{"id":"2305.02171","title":"Continual Reasoning: Non-Monotonic Reasoning in Neurosymbolic AI using Continual Learning","created":"2023-05-03","cited_by_count":0,"area":"lr"},{"id":"2408.16098","title":"Structured Event Reasoning with Large Language Models","created":"2024-08-28","cited_by_count":0,"area":"lr"},{"id":"2508.03170","title":"Quantum Spectral Reasoning: A Non-Neural Architecture for Interpretable Machine Learning","created":"2025-08-05","cited_by_count":0,"area":"lr"},{"id":"2508.14923","title":"A Fully Spectral Neuro-Symbolic Reasoning Architecture with Graph Signal Processing as the Computational Backbone","created":"2025-08-19","cited_by_count":0,"area":"lr"},{"id":"2511.10655","title":"Spectral Neuro-Symbolic Reasoning II: Semantic Node Merging, Entailment Filtering, and Knowledge Graph Alignment","created":"2025-11-02","cited_by_count":0,"area":"lr"},{"id":"2602.10732","title":"Macaron: Controlled, Human-Written Benchmark for Multilingual and Multicultural Reasoning via Template-Filling","created":"2026-02-11","cited_by_count":0,"area":"lr"},{"id":"2602.19160","title":"Reasoning Capabilities of Large Language Models. Lessons Learned from General Game Playing","created":"2026-02-22","cited_by_count":0,"area":"lr"},{"id":"2604.14641","title":"Learning to Draw ASCII Improves Spatial Reasoning in Language Models","created":"2026-04-16","cited_by_count":0,"area":"lr"},{"id":"2606.13020","title":"SciR: A Controllable Benchmark for Scientific Reasoning in LLMs","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2606.17905","title":"ChLogic: Evaluating Robustness of Logical Reasoning in Chinese Expressions","created":"2026-06-16","cited_by_count":0,"area":"lr"},{"id":"2607.03957","title":"NormWorlds-CF: Solver-Verified Counterfactual Normative Reasoning with Metamorphic-Relation GRPO","created":"2026-07-04","cited_by_count":0,"area":"lr"},{"id":"2608.03882","title":"MultiGlobeQA: A Multilingual and Globally Diverse Benchmark for Geospatial Reasoning","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2609.26060","title":"ChainUQ: Reasoning Consistency-Aware Uncertainty Quantification for Large Language Models","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2609.35486","title":"Who Is Left of Whom? Tracing Spatial Evidence and Role Binding in Relative-Position Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}