{"total":20,"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":"2406.17169","title":"Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models","created":"2024-06-24","cited_by_count":39,"area":"lr"},{"id":"2310.05253","title":"Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models","created":"2023-10-08","cited_by_count":37,"area":"lr"},{"id":"2310.13552","title":"Self-prompted Chain-of-Thought on Large Language Models for Open-domain Multi-hop Reasoning","created":"2023-10-20","cited_by_count":21,"area":"lr"},{"id":"2407.18553","title":"REAPER: Reasoning based Retrieval Planning for Complex RAG Systems","created":"2024-07-26","cited_by_count":16,"area":"lr"},{"id":"2412.10079","title":"Lost in the Middle, and In-Between: Enhancing Language Models' Ability to Reason Over Long Contexts in Multi-Hop QA","created":"2024-12-13","cited_by_count":13,"area":"lr"},{"id":"2509.21199","title":"A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QA","created":"2025-09-25","cited_by_count":9,"area":"lr"},{"id":"2601.04525","title":"GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence","created":"2026-01-08","cited_by_count":7,"area":"lr"},{"id":"2310.16731","title":"Disentangling Extraction and Reasoning in Multi-hop Spatial Reasoning","created":"2023-10-25","cited_by_count":6,"area":"lr"},{"id":"2506.02591","title":"On Generalization across Measurement Systems: LLMs Entail More Test-Time Compute for Underrepresented Cultures","created":"2025-06-03","cited_by_count":5,"area":"lr"},{"id":"2211.08466","title":"Reasoning Circuits: Few-shot Multihop Question Generation with Structured Rationales","created":"2022-11-15","cited_by_count":3,"area":"lr"},{"id":"2504.16414","title":"Evaluating Multi-Hop Reasoning in Large Language Models: A Chemistry-Centric Case Study","created":"2025-04-23","cited_by_count":3,"area":"lr"},{"id":"2505.11811","title":"BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering","created":"2025-05-17","cited_by_count":3,"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":"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":"2309.12767","title":"Furthest Reasoning with Plan Assessment: Stable Reasoning Path with Retrieval-Augmented Large Language Models","created":"2023-09-22","cited_by_count":2,"area":"lr"},{"id":"2403.01969","title":"AS-ES Learning: Towards Efficient CoT Learning in Small Models","created":"2024-03-04","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":"2606.15971","title":"SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges","created":"2026-06-14","cited_by_count":1,"area":"lr"},{"id":"2608.12129","title":"SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges","created":"2026-08-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}