When Does Longer Reasoning Help? Predicting Mathematical Reasoning Through Discovery and Execution

arXiv:2610.05322v1 Announce Type: new Abstract: Test-time compute can improve mathematical reasoning, but can short-budget runs predict how mathematical reasoning scales with additional compute? We introduce a Discovery--Execution (DE) framework that predicts the aggregate held-out scaling curves through a convolution of strategy discovery and conditional execution. From independent short-budget attempts and oracle-sketch-conditioned runs, the framework estimates cumulative success along held-out reasoning trajectories under alternate compute allocations. We evaluate four models on 35 fresh Olympiad problems and non-geometry problems from IMO-ProofBench Advanced. Under the DE framework, near-saturated execution predicts geometric scaling, as observed for the GPT models. For Claude Opus 4.8, incorporating measured execution substantially improves held-out forecasts over geometric extrapolation across one- and two-arm allocations. As a secondary application, regularized DE (R-DE) decisions to continue or restart yield lower average regret than the best model-specific retrospective policy. Together, these results show that measuring conditional execution provides information about longer reasoning that short-budget success rates do not always capture.

Related

• Hidden States as Early Signals: Step-level Trace Evaluation and Pruning for Efficient Test-Time Scaling
• When Does Structured Knowledge Help Neural Theorem Proving?
• Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization
• ATLAS: Agentic Test-time Learning-to-Allocate Scaling

Source: arXiv cs.LG | 2026-10-06