XDomainBench: Diagnosing Reasoning Collapse in High-Dimensional Scientific Knowledge Composition

TL;DR

XDomainBench is a new benchmark designed to evaluate the reasoning capabilities of Large Language Models in complex, interdisciplinary scientific tasks, revealing systematic reasoning failures as task complexity increases.

Contribution

The paper introduces XDomainBench, a comprehensive diagnostic benchmark for interactive scientific reasoning across multiple domains and task complexities.

Findings

LLMs exhibit reasoning collapse with increased composition complexity.

Domain composition directly increases task difficulty.

Error accumulation and domain confusion cause session failures.

Abstract

Large Language Models (LLMs) are increasingly deployed for knowledge synthesis, yet their capacity for compositional generalization in scientific knowledge remains under-characterized. Existing benchmarks primarily focus on single-turn restricted scenarios, failing to capture the capability boundaries exposed by real-world interactive scientific workflows. To address this, we introduce XDomainBench, a diagnostic benchmark for interactive interdisciplinary scientific reasoning. We formalize the composition order and mixture structure to enable systematic stress-testing from single-discipline to inter-disciplinary, comprising 8,598 interactive sessions across 20 domains and 4 task categories, with 8 realistic trajectory patterns covering difficulty and domain-mixture dynamics, simulating real AI4S scenarios. Large-scale evaluation of LLMs reveals a systematic reasoning collapse as composition order increases, stemming from two root causes: (i) direct difficulty increases induced by domain composition, and (ii) indirect interaction-amplified failures where trajectory patterns trigger error accumulation, reasoning breaks, and domain confusion, ultimately leading to session collapse.