{"total":14,"rows":[{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162,"area":"lr"},{"id":"2505.08638","title":"TRAIL: Trace Reasoning and Agentic Issue Localization","created":"2025-05-13","cited_by_count":104,"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":"2503.07832","title":"RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code","created":"2025-03-10","cited_by_count":30,"area":"lr"},{"id":"2409.02257","title":"MMLU-Pro+: Evaluating Higher-Order Reasoning and Shortcut Learning in LLMs","created":"2024-09-03","cited_by_count":16,"area":"lr"},{"id":"2201.06777","title":"COPA-SSE: Semi-structured Explanations for Commonsense Reasoning","created":"2022-01-18","cited_by_count":8,"area":"lr"},{"id":"2511.14366","title":"ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning","created":"2025-11-18","cited_by_count":6,"area":"lr"},{"id":"2306.09918","title":"No Strong Feelings One Way or Another: Re-operationalizing Neutrality in Natural Language Inference","created":"2023-06-16","cited_by_count":4,"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":"2209.07760","title":"Possible Stories: Evaluating Situated Commonsense Reasoning under Multiple Possible Scenarios","created":"2022-09-16","cited_by_count":3,"area":"lr"},{"id":"2603.29025","title":"The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning","created":"2026-03-30","cited_by_count":1,"area":"lr"},{"id":"2607.07229","title":"Reasoning Consistency Scanning: A Framework for Auditing Chain-of-Thought Validity in AI Safety Evaluations","created":"2026-07-08","cited_by_count":0,"area":"lr"},{"id":"2609.09372","title":"What Does MMLU Actually Measure? A Psychometric Audit of Difficulty Structure in Aggregate Benchmark Scores","created":"2026-09-08","cited_by_count":0,"area":"lr"},{"id":"2609.13009","title":"How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks","created":"2026-09-11","cited_by_count":0,"area":"lr"}],"next_cursor":null}