paper-with-me

Papers

ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning

2026-06-05 · Vladislav Smirnov, Chieu Nguyen, Sergey Senichev, Minh Ngoc Ta, Ekaterina Fadeeva, Artem Vazhentsev, Daria Galimzianova, Nikolai Rozanov, Viktor Mazanov, Jingwei Ni, Tianyi Wu, Igor Kiselev, Mrinmaya Sachan, Iryna Gurevych, Preslav Nakov, Timothy Baldwin, Artem Shelmanov arxiv

Test-time compute (TTC) scaling has emerged as a powerful paradigm for improving large language model (LLM) reasoning by allocating additional compute during inference, e.g., via multi-sample generation and verifier-based reranking. Existing TTC scaling strategies and reasoning scorers remain fragmented, evaluated under inconsistent protocols, and are rarely analyzed through the lens of quality-cost trade-offs. We introduce ThinkBooster, a unified framework for seamless test-time compute scaling of LLM reasoning, which consists of (i) a modular Python library implementing state-of-the-art TTC scaling strategy and scorer families, (ii) a benchmark that jointly evaluates performance and computational efficiency, and (iii) a deployable OpenAI-compatible proxy service that enables drop-in integration of adaptive reasoning into real-world applications. We further provide a demo visual debugger for inspecting the reasoning trajectories, intermediate selection decisions, and alternative reasoning paths. Empirical results on mathematical and coding tasks reveal the performance-compute trade-offs of TTC scaling strategies and scoring methods and demonstrate that ThinkBooster provides practical gains in real-world tasks. The code is available online under an MIT license.

📄 PDF Abstract BibTeX arXiv:2606.06915

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Similar Papers 제목 키워드 기반

MetAdv: A Unified and Interactive Adversarial Testing Platform for Autonomous Driving

2025-08-04 · Aishan Liu, Jiakai Wang, Tianyuan Zhang, Hainan Li 외 arxiv

Evaluating and ensuring the adversarial robustness of autonomous driving (AD) systems is a critical and unresolved challenge. This paper introduces MetAdv, a novel adversarial testing platform that enables realistic, dyn…

Adversarial RobustnessAutonomous Driving

Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results

2022-04-07 · Tal Ridnik, Hussam Lawen, Emanuel Ben-Baruch, Asaf Noy

ImageNet serves as the primary dataset for evaluating the quality of computer-vision models. The common practice today is training each architecture with a tailor-made scheme, designed and tuned by an expert. In this pap…

Image ClassificationKnowledge Distillation

LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models

2026-02-15 · Shufan Li, Yuchen Zhu, Jiuxiang Gu, Kangning Liu 외 arxiv

Diffusion language models (dLLMs) recently emerged as a promising alternative to auto-regressive LLMs. The latest works further extended it to multimodal understanding and generation tasks. In this work, we propose LaViD…

Reinforcement LearningImage Editing

SCPP: A Unified Python Library for Soft Clustering

2026-07-21 · Kiyan Rezaee, Morteza Ziabakhsh, Artin Bahrampour, Seyed Mohammad Ghoreishi 외 arxiv

In this paper, we present SCPP (Soft Clustering Python Package), an open-source Python framework for soft clustering. SCPP establishes a canonical, scikit-learn-compatible estimator interface that standardizes model trai…

SeamlessM4T: Massively Multilingual & Multimodal Machine Translation

2023-08-22 · Seamless Communication, Loïc Barrault, Yu-An Chung, Mariano Cora Meglioli 외

What does it take to create the Babel Fish, a tool that can help individuals translate speech between any two languages? While recent breakthroughs in text-based models have pushed machine translation coverage beyond 200…

Automatic Speech RecognitionMachine TranslationSpeech-to-Speech TranslationSpeech-to-Text+5