{"total":22,"rows":[{"id":"2409.12941","title":"Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation","created":"2024-09-19","cited_by_count":162,"area":"lr"},{"id":"2502.12289","title":"Evaluating Step-by-step Reasoning Traces: A Survey","created":"2025-02-17","cited_by_count":63,"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":"2502.05078","title":"Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structures","created":"2025-02-07","cited_by_count":16,"area":"lr"},{"id":"2507.17365","title":"DynaSearcher: Dynamic Knowledge Graph Augmented Search Agent via Multi-Reward Reinforcement Learning","created":"2025-07-23","cited_by_count":14,"area":"lr"},{"id":"2505.22240","title":"BioHopR: A Benchmark for Multi-Hop, Multi-Answer Reasoning in Biomedical Domain","created":"2025-05-28","cited_by_count":10,"area":"lr"},{"id":"2602.19127","title":"AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAG","created":"2026-02-22","cited_by_count":5,"area":"lr"},{"id":"2506.14927","title":"MDBench: A Synthetic Multi-Document Reasoning Benchmark Generated with Knowledge Guidance","created":"2025-06-17","cited_by_count":3,"area":"lr"},{"id":"2512.15663","title":"Explaining the Reasoning of Large Language Models Using Attribution Graphs","created":"2025-12-17","cited_by_count":3,"area":"lr"},{"id":"2601.12499","title":"Failure Modes in Multi-Hop QA: The Weakest Link Effect and the Recognition Bottleneck","created":"2026-01-18","cited_by_count":3,"area":"lr"},{"id":"2506.10527","title":"LogiPlan: A Structured Benchmark for Logical Planning and Relational Reasoning in LLMs","created":"2025-06-12","cited_by_count":2,"area":"lr"},{"id":"2603.29085","title":"PAR$^2$-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering","created":"2026-03-30","cited_by_count":2,"area":"lr"},{"id":"2605.19228","title":"Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution","created":"2026-05-19","cited_by_count":2,"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":"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":"2603.05818","title":"RouteGoT: Node-Adaptive Routing for Cost-Efficient Graph of Thoughts Reasoning","created":"2026-03-06","cited_by_count":0,"area":"lr"},{"id":"2603.16654","title":"Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models","created":"2026-03-17","cited_by_count":0,"area":"lr"},{"id":"2604.08124","title":"Beyond Stochastic Exploration: What Makes Training Data Valuable for Agentic Search","created":"2026-04-09","cited_by_count":0,"area":"lr"},{"id":"2605.22358","title":"Integrating Chain-of-Thought into Generative Retrieval: A Preliminary Study","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2609.36984","title":"REALHOP: Rethinking Multi-Hop Reasoning Evaluation via Behavioral Auditing","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.00940","title":"ReHoPER: Receding-Horizon Planning for Enhanced Reasoning","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}