{"total":26,"rows":[{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004,"area":"lr"},{"id":"2406.11050","title":"A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners","created":"2024-06-16","cited_by_count":73,"area":"lr"},{"id":"2412.13147","title":"Are Your LLMs Capable of Stable Reasoning?","created":"2024-12-17","cited_by_count":65,"area":"lr"},{"id":"2506.12286","title":"The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason","created":"2025-06-14","cited_by_count":49,"area":"lr"},{"id":"2407.08733","title":"Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist","created":"2024-07-11","cited_by_count":48,"area":"lr"},{"id":"2405.19616","title":"Easy Problems That LLMs Get Wrong","created":"2024-05-30","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":"2406.06196","title":"LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages","created":"2024-06-10","cited_by_count":28,"area":"lr"},{"id":"2402.11924","title":"Cofca: A Step-Wise Counterfactual Multi-hop QA benchmark","created":"2024-02-19","cited_by_count":27,"area":"lr"},{"id":"2406.17271","title":"DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph","created":"2024-06-25","cited_by_count":26,"area":"lr"},{"id":"2312.02143","title":"Competition-Level Problems are Effective LLM Evaluators","created":"2023-12-04","cited_by_count":25,"area":"lr"},{"id":"2401.17882","title":"I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench","created":"2024-01-31","cited_by_count":21,"area":"lr"},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2406.10621","title":"StrucText-Eval: Evaluating Large Language Model's Reasoning Ability in Structure-Rich Text","created":"2024-06-15","cited_by_count":13,"area":"lr"},{"id":"2412.14368","title":"Beyond Math: Stories as a Testbed for Memorization-Constrained Reasoning in LLMs","created":"2024-12-18","cited_by_count":12,"area":"lr"},{"id":"2506.15455","title":"RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation","created":"2025-06-18","cited_by_count":11,"area":"lr"},{"id":"2509.21459","title":"A State-of-the-Art SQL Reasoning Model using RLVR","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2510.24427","title":"SynthWorlds: Controlled Parallel Worlds for Disentangling Reasoning and Knowledge in Language Models","created":"2025-10-28","cited_by_count":5,"area":"lr"},{"id":"2603.09678","title":"EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Languages","created":"2026-03-10","cited_by_count":4,"area":"lr"},{"id":"2503.02972","title":"LINGOLY-TOO: Disentangling Reasoning from Knowledge with Templatised Orthographic Obfuscation","created":"2025-03-04","cited_by_count":3,"area":"lr"},{"id":"2505.22661","title":"GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and Reasoning","created":"2025-05-28","cited_by_count":3,"area":"lr"},{"id":"2506.11128","title":"Theory-Grounded Evaluation of Human-Like Fallacy Patterns in LLM Reasoning","created":"2025-06-10","cited_by_count":2,"area":"lr"},{"id":"2608.02442","title":"Right Answer, Wrong Method: Shortcut Hacking Misleads the Evaluation of LLM Reasoning on Frontier Science Benchmarks","created":"2026-08-03","cited_by_count":2,"area":"lr"},{"id":"2605.02442","title":"Measuring AI Reasoning: A Guide for Researchers","created":"2026-05-04","cited_by_count":1,"area":"lr"},{"id":"2605.29087","title":"The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2608.30413","title":"DERELAB: Probing Defeasible Reasoning and Confirmation Bias in LLMs with a Generative Benchmark","created":"2026-08-31","cited_by_count":1,"area":"lr"}],"next_cursor":null}