Searcharxiv⌕ Search

arXiv subjects

Benoit Dumoulin

Publications and source records attributed to Benoit Dumoulin.

21 records · Page 2Linked to original sources

Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search

Large Language Models (LLMs) have achieved significant advances in reasoning tasks. A key approach is tree-based search with verifiers, which expand candidate reasoning paths and use reward models to guide pruning and selection. Although effective in improving accuracy, these methods are not optimal in terms of efficiency: they perform simple decomposition on the reasoning process, but ignore the planning-execution nature of tasks such as math reasoning or code generation. This results in inefficient exploration of reasoning process. To address this, we propose a dual-phase test-time scaling framework that explicitly separates reasoning into planning and execution, and performs search over the two phases individually. Specifically, we decompose reasoning trajectories and develop reward models for each phase, enabling the search to explore and prune plans and executions separately. We further introduce a dynamic budget allocation mechanism that adaptively redistributes sampling effort based on reward feedback, allowing early stopping on confident steps and reallocation of computation to more challenging parts of the reasoning process. Experiments on both mathematical reasoning and code generation benchmarks demonstrate that our approach consistently improves accuracy while reducing redundant computation.

cs.AI↗

Explore-Exploit: A Framework for Interactive and Online Learning

Interactive user interfaces need to continuously evolve based on the interactions that a user has (or does not have) with the system. This may require constant exploration of various options that the system may have for the user and obtaining signals of user preferences on those. However, such an exploration, especially when the set of available options itself can change frequently, can lead to sub-optimal user experiences. We present Explore-Exploit: a framework designed to collect and utilize user feedback in an interactive and online setting that minimizes regressions in end-user experience. This framework provides a suite of online learning operators for various tasks such as personalization ranking, candidate selection and active learning. We demonstrate how to integrate this framework with run-time services to leverage online and interactive machine learning out-of-the-box. We also present results demonstrating the efficiencies that can be achieved using the Explore-Exploit framework.

cs.LG↗

Theory of Lattice and Electronic Fluctuations in Weakly Localized Spin-Peierls Systems

A theoretical approach to the influence of one-dimensional lattice fluctuations on electronic properties in weakly localized spin-Peierls systems is proposed using the renormalization group and the functional integral techniques. The interplay between the renormalization group flow of correlated electrons and one-dimensional lattice fluctuations is taken into account by the one-dimensional functional integral method in the adiabatic limit. Calculations of spin-Peierls precursor effects on response functions are carried out explicitely and the prediction for the temperature dependent magnetic susceptibility and nuclear relaxation is compared with available experimental data for (TMTTF)$_{2}$PF$_{6}$.

cond-mat↗