Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability (2026.acl-long)
Copied to clipboard
Xiao Liang, Zhong-Zhi Li, Zhenghao Lin, Eric Hanchen Jiang, Hengyuan Zhang, Yelong Shen, Kai-Wei Chang, Ying Nian Wu, Yeyun Gong, Weizhu Chen
| Challenge: | Large language models have demonstrated strong reasoning capabilities through step-by-step chain-of-thought (CoT) reasoning, but their strictly sequential nature constrains test-time scalability. |
| Approach: | They propose an end-to-end reinforcement learning framework to enhance LLMs' DAC-style reasoning capacity by decomposing a problem into subproblems and solving them sequentially. |
| Outcome: | The proposed model surpasses CoT by 8.6% and 6.3% on competition-level benchmarks and is available at the [github.com/MasterVito/DAC-RL]. |
Similar Papers
Recursion of Thought: A Divide-and-Conquer Approach to Multi-Context Reasoning with Language Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to generate intermediate steps (CoT) are limited by the maximum context size due to various reasons. |
| Approach: | They propose a new inference framework that introduces several special tokens that the models can output to trigger context-related operations. |
| Outcome: | Extensive experiments with multiple architectures including GPT-3 show that the proposed framework significantly improves LMs’ inference capability. |
Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling (2026.findings-acl)
Copied to clipboard
Ivan Rodkin, Daniil Orel, Konstantin Smirnov, Arman Bolatov, Bilal Elbouardi, Besher Hassan, Yuri Kuratov, Aydar Bulatov, Preslav Nakov, Timothy Baldwin, Artem Shelmanov, Mikhail Burtsev
| Challenge: | Reasoning is a core capability of large language models, yet how multi-step reasoning is learned and executed remains unclear. |
| Approach: | They evaluate how large language models learn multi-step reasoning without memorization . they find that most neural architectures trained from scratch can learn rule inference . |
| Outcome: | The proposed framework fails to solve a natural-language proxy task with high accuracy. |
Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models (2025.emnlp-main)
Copied to clipboard
Kaiyan Chang, Yonghao Shi, Chenglong Wang, Hang Zhou, Chi Hu, Xiaoqian Liu, Yingfeng Luo, Yuan Ge, Tong Xiao, JingBo Zhu
| Challenge: | Recent training-based TTS methods, such as continued reinforcement learning, have surged in popularity, while training-free TTS approaches are gradually fading from prominence. |
| Approach: | They propose a fine-grained sequential scaling method guided by process verification that integrates training-free TTS methods with other classical parallel scaling methods at the step level. |
| Outcome: | Experiments on five instruction-tuned large language models (LLMs) show that training-free TTS methods can extend reasoning performance boundaries. |
ReEfBench: Quantifying the Reasoning Efficiency of LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for Chain-of-Thought evaluations do not distinguish between genuine reasoning and mere verbosity. |
| Approach: | They propose a framework for the non-intrusive, comprehensive process-centric evaluation of reasoning grounded in First-Order Logic. |
| Outcome: | The proposed framework identifies four distinct behavioral prototypes and diagnoses the failure modes. |
Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Generative Reward Models have demonstrated that scaling the length of Chain-of-Thought reasoning enhances reliability of evaluation. |
| Approach: | They propose a framework that reconfigures raw rationales into structured Breadth-CoT and Depth-Co T through a modular synthesis pipeline. |
| Outcome: | The proposed framework surpasses open-source RMs by an average of 8.2%. |
Correct, Concise and Complete: Multi-stage Training For Adaptive Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) increase test-time computation, often in the form of chain-of-thought (CoT) however, reasoning traces can become unnecessarily long, increasing computation costs without improving accuracy and sometimes even degrading performance. |
| Approach: | They propose a multi-stage efficient reasoning method that combines supervised fine-tuning with reinforcement learning using an adaptive length penalty. |
| Outcome: | The proposed method reduces response length by an average of 28% for 8B models and 40% for 32B models while incurring only minor performance drops of 1.6 and 2.5 points, respectively. |
One Missing Piece for Open-Source Reasoning Models: A Dataset to Mitigate Cold-Starting Short CoT LLMs in RL (2025.acl-industry)
Copied to clipboard
Hyungjoo Chae, Dongjin Kang, Jihyuk Kim, Beong-woo Kwak, Sunghyun Park, Haeju Park, Jinyoung Yeo, Moontae Lee, Kyungjae Lee
| Challenge: | Existing large reasoning models are limited by their closed nature and high API costs and safety issues. |
| Approach: | They propose to build a long CoT dataset with existing short CoT LLMs that are not trained for inference-time scaling. |
| Outcome: | The proposed model achieves quality comparable to—or slightly below—R1 and is able to think longer and provide control over the thought budget to better manage the overthinking problem. |
LLM×MapReduce: Simplified Long-Sequence Processing using Large Language Models (2025.acl-long)
Copied to clipboard
Zihan Zhou, Chong Li, Xinyi Chen, Shuo Wang, Yu Chao, Zhili Li, Haoyu Wang, Qi Shi, Zhixing Tan, Xu Han, Xiaodong Shi, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing studies have focused on extending the context length of large language models (LLMs) due to their quadratic computational complexity and a lack of high-quality long training examples, most LLMs are trained with a limited window size. |
| Approach: | They propose a training-free framework that enables large language models to effectively process long texts using a divide-and-conquer strategy for comprehensive document understanding. |
| Outcome: | The proposed framework outperforms open-source and commercial long-context LLMs and is compatible with several models. |
Training-Free Test-Time Contrastive Learning for Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing training-free alternatives to training-based models are static or depend on external guidance. |
| Approach: | They propose a training-free adaptation framework that enables a frozen LLM to improve online by distilling supervision from its own inference experiences. |
| Outcome: | The proposed framework outperforms existing test-time adaptation methods under online evaluation. |
A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions (2026.acl-long)
Copied to clipboard
Zhiyin Yu, Yuchen Mou, Juncheng Yan, Junyu Luo, Chunchun Chen, Xing Wei, Yunhui Liu, Hongru Sun, Yuxing Zhang, Jun Xu, Yatao Bian, Ming Zhang, Wei Ye, Tieke He, Jie Yang, Guanjie Zheng, Zhonghai Wu, Bo Zhang, Lei Bai, Xiao Luo
| Challenge: | Existing research on reinforcement learning for LLMs under data scarcity has not been unified. |
| Approach: | They propose a top-up hierarchical framework built around three complementary perspectives: data-centric, training-centric and framework-centric. |
| Outcome: | The proposed framework provides a clear conceptual foundation for understanding the design space of data-efficient RL for large language models and to guide researchers working in this emerging area. |