Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis

Anushka Yadav, Isha Nalawade, Srujana Pillarichety, Yashwanth Babu Vunnam, Samyadeep Basu, Reshmi Ghosh, Wenlong Zhao, Ali Naseh, Sriram Balasubramanian, Soundararajan Srinivasan

Keywords: Reasoning Models, Failure Patterns, DeepSeek, Extractive QA, Conversational Search, Claude, LLaMa

TL;DR: In real-world conversational search requiring reasoning across multiple snippets, reasoning LMs often find the right answer but still fumble on complex multi-hop tasks—overthinking, missing hops, and chasing irrelevant detours.

Abstract:

The emergence of reasoning models and their integration into practical AI chat bots has led to breakthroughs in solving advanced math, deep search, and extractive question answering problems that requires a complex and multi-step thought process. Yet, a complete understanding of why these models hallucinate more than general purpose language models is missing.
In this investigative study, we systematically explore reasoning failures of contemporary language models on multi-hop question answering tasks. We introduce a novel, nuanced error categorization framework that examines failures across three critical dimensions: the diversity and uniqueness of source documents involved ("hops"), completeness in capturing relevant information ("coverage"), and cognitive inefficiency ("overthinking"). Through rigorous human annotation, supported by complementary automated metrics, our exploration uncovers intricate error patterns often hidden by accuracy-centric evaluations. This investigative approach provides deeper insights into the cognitive limitations of current models and offers actionable guidance toward enhancing reasoning fidelity, transparency, and robustness in future language modeling efforts.

Submission Number: 99