{"total":19,"rows":[{"id":"2502.12289","title":"Evaluating Step-by-step Reasoning Traces: A Survey","created":"2025-02-17","cited_by_count":63,"area":"lr"},{"id":"2504.04736","title":"Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use","created":"2025-04-07","cited_by_count":45,"area":"lr"},{"id":"2406.13397","title":"MoreHopQA: More Than Multi-hop Reasoning","created":"2024-06-19","cited_by_count":37,"area":"lr"},{"id":"2502.16268","title":"ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning","created":"2025-02-22","cited_by_count":17,"area":"lr"},{"id":"2508.13250","title":"Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Information","created":"2025-08-18","cited_by_count":17,"area":"lr"},{"id":"2503.10691","title":"Reasoning is All You Need for Video Generalization: A Counterfactual Benchmark with Sub-question Evaluation","created":"2025-03-12","cited_by_count":6,"area":"lr"},{"id":"2504.06460","title":"Can LLMs Simulate Personas with Reversed Performance? A Systematic Investigation for Counterfactual Instruction Following in Math Reasoning Context","created":"2025-04-08","cited_by_count":3,"area":"lr"},{"id":"2509.17380","title":"Correlation or Causation: Analyzing the Causal Structures of LLM and LRM Reasoning Process","created":"2025-09-22","cited_by_count":3,"area":"lr"},{"id":"2603.07931","title":"BRIDGE: Benchmark for multi-hop Reasoning In long multimodal Documents with Grounded Evidence","created":"2026-03-09","cited_by_count":3,"area":"lr"},{"id":"2605.01248","title":"$S^3$-R1: Learning to Retrieve and Answer Step-by-Step with Synthetic Data","created":"2026-05-02","cited_by_count":3,"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":"2504.04150","title":"Reasoning on Multiple Needles In A Haystack","created":"2025-04-05","cited_by_count":2,"area":"lr"},{"id":"2507.18368","title":"Reasoning Beyond the Obvious: Evaluating Divergent and Convergent Thinking in LLMs for Financial Scenarios","created":"2025-07-24","cited_by_count":1,"area":"lr"},{"id":"2510.08800","title":"Benchmarking Chinese Commonsense Reasoning with a Multi-hop Reasoning Perspective","created":"2025-10-09","cited_by_count":1,"area":"lr"},{"id":"2601.07794","title":"Kinship Data Benchmark for Multi-hop Reasoning","created":"2026-01-12","cited_by_count":1,"area":"lr"},{"id":"2601.19827","title":"When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering","created":"2026-01-27","cited_by_count":1,"area":"lr"},{"id":"2603.13091","title":"Reasoning over Video: Evaluating How MLLMs Extract, Integrate, and Reconstruct Spatiotemporal Evidence","created":"2026-03-13","cited_by_count":1,"area":"lr"},{"id":"2607.10562","title":"CRiT-QA: Evaluating Multi-hop Reasoning with Counterfactual Chains and Distractor Traps","created":"2026-07-12","cited_by_count":1,"area":"lr"},{"id":"2609.35312","title":"MemoReason: Evaluating the Effect of Parametric Memory on Contextual Reasoning in LLMs","created":"2026-09-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}