ReasonOps: Operator Segmentation for LLM Reasoning Traces

Daniel Lee, Owen Queen, James Zou

Keywords: Automated interpretability, Benchmarking Interpretability, Applications of interpretability

TL;DR: Segmentation for reasoning traces via interpretable operators

Abstract: Chain-of-thought traces from large reasoning models can span tens of thousands of tokens, yet we lack a vocabulary for describing their internal structure. Previous methods developed to analyze chain-of-thought traces are either too rigid or not expressive enough, failing to capture features across domains and models. To remedy this, we develop ReasonOps, an unsupervised, expressive method for annotating chain-of-thought traces, providing succinct universal operators. Using ReasonOps, we analyze 44,662 traces from 12 thinking LLMs spanning 6 families across 8 reasoning benchmarks and discover that they share a common compositional structure: 7 recurring reasoning operators---discourse-level moves such as backtracking, inferring, and hypothesizing---that emerge from unsupervised clustering of sentence-initial 3-token pivots. These operators appear across every model family and benchmark domain, confirmed by three independent LLM judges who classify held-out samples at 70--76\% accuracy. We analyze the structure of operators on easy vs. hard problems, revealing that reflective operators are more helpful on hard problems and harm performance on easy problems. Operator sequences are highly model-identifying: a classifier trained on operator distributions alone recovers the source model with macro-AUC $= 0.987$, revealing that each model family has a distinctive reasoning fingerprint. Structural operator features predict within-problem answer correctness well above baselines. Classifiers built on these operators reach WP-AUC $= 0.701$ and $0.801$ on AIME specifically. ReasonOps further enables early quality estimation well before the trace completes: we predict at WP-AUC $= 0.664$ for only 50\% of the trace. The ReasonOps pipeline is unsupervised and annotation-free, enabling deep insights into LLM reasoning traces as well as strong downstream results on model identification and correctness prediction.

Submission Number: 204