RECOR: Reasoning-Focused Multi-Turn Conversational Retrieval Benchmark

RECOR: Reasoning-Focused Multi-Turn Conversational Retrieval Benchmark

Mohammed Ali, Abdelrahman Abdallah, Amit Agarwal, Hitesh Laxmichand Patel, Adam Jatowt. arXiv (2026).

Publisher arXiv X/Twitter LinkedIn Email

Abstract. RECOR is a benchmark for reasoning-intensive conversational retrieval. It combines multi-turn search with explicit retrieval reasoning, enabling evaluation of systems that must use both conversation history and reasoning to retrieve the right evidence.

Related Papers

• MVTamperBench: Evaluationuating Robustness of Vision-Language Models ACL (2024)
• SweEvaluation: Do LLMs Really Swear? A Safety Benchmark for Testing Limits for Enterprise Use NAACL (2024)
• Vlmevalkit: An Open-Source Toolkit for Evaluationuating Large Multi-Modality Models ACM (2024)
• A Diagnostic Framework for Auditing Reference-Free Vision-Language Metrics IJCNLP (2025)
• Accesseval: Benchmarking Disability Bias in Large Language Models EMNLP (2025)