Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning
Abstract
Majority voting has proven effective for close-ended question answering by aggregating parallel reasoning traces. However, it is not directly applicable to open-ended reasoning, such as code generation and web-based deep research, where a “majority” over complete solutions is ill-defined. We introduce THINKMERGE, a training-free, plug-and-play decoding strategy that runs K parallel reasoning traces and averages their next-token logits at synchronization points to produce a single coherent output. THINKMERGE integrates seamlessly with vLLM/SGLang and remains compatible with standard decoding techniques such as Top-p/Top-k. Empirically, it matches or surpasses majority voting on AIME and GPQA, while delivering consistent gains on open-ended coding tasks: on LiveCodeBench (hard), pass@1 improves by +8.28% for DeepCoder-14B-Preview and +7.58% for Qwen3-8B. Beyond code, we further show that THINKMERGE improves web-based deep-research agents (e.g., WebSailor-7B/32B) across GAIA, BrowseComp-en/zh, and XbenchDeepSearch. These results demonstrate that parallel test-time scaling can benefit open-ended reasoning without relying on voting over complete outputs.
Cite
Text
Wang et al. "Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning." International Conference on Learning Representations, 2026.Markdown
[Wang et al. "Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning." International Conference on Learning Representations, 2026.](https://mlanthology.org/iclr/2026/wang2026iclr-think/)BibTeX
@inproceedings{wang2026iclr-think,
title = {{Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning}},
author = {Wang, Haonan and Du, Chao and Kawaguchi, Kenji and Pang, Tianyu},
booktitle = {International Conference on Learning Representations},
year = {2026},
url = {https://mlanthology.org/iclr/2026/wang2026iclr-think/}
}