AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time (2025.emnlp-main)
Copied to clipboard
Junyu Zhang, Runpei Dong, Han Wang, Xuying Ning, Haoran Geng, Peihao Li, Xialin He, Yutong Bai, Jitendra Malik, Saurabh Gupta, Huan Zhang
| Challenge: | Existing monotonic scaling methods for large reasoning models are not reliable. |
| Approach: | They propose a universal framework for modulating reasoning progress in large reasoning models at test time. |
| Outcome: | The proposed framework unifies and generalizes existing monotonic scaling methods and enables flexible and dense slow-to-fast reasoning modulation. |
Similar Papers
Thinking Long, but Short: Stable Sequential Test-Time Scaling for Large Reasoning Models (2026.findings-eacl)
Copied to clipboard
| Challenge: | Inducing models to think for longer can increase accuracy, but as the length of reasoning is further extended, it has also been shown to result in accuracy degradation and model instability. |
| Approach: | They propose a sequential test-time scaling method which induces models to think for longer, but which also generates an increasingly long output. |
| Outcome: | The proposed method improves model accuracy significantly over a wide range of induced thoughts, stabilizing the accuracy of sequential scaling, and eliminating the need for reasoning length fine-tuning. |
Thought calibration: Efficient and confident test-time scaling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for teaching language models to be economical with their token budgets have failed to achieve the desired results. |
| Approach: | They propose to calibrate a language model's growing body of thoughts to determine when new reasoning plateaus. |
| Outcome: | The proposed framework preserves model performance with up to 60% reduction in thinking tokens on in-distribution data, and up to 20% in out-of-difference data. |
Z1: Efficient Test-time Scaling with Code (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can achieve enhanced complex problem-solving through test-time computing scaling, but this often entails longer contexts and numerous reasoning token costs. |
| Approach: | They propose an efficient test-time scaling method that trains LLMs on code-related reasoning trajectories and a novel Shifted Thinking Window to mitigate overthinking overhead. |
| Outcome: | The proposed method reduces overthinking overhead while maintaining performance. |
Scaling Evaluation-Time Compute with Reasoning Models as Evaluators (2026.findings-acl)
Copied to clipboard
Seungone Kim, Ian Wu, Jinu Lee, Xiang Yue, Seongyun Lee, Minkyeong Moon, Carolin Lawrence, Kiril Gashteovski, Julia Hockenmaier, Graham Neubig, Sean Welleck
| Challenge: | Language model (LM) evaluators that generate chain-of-thought reasoning are widely used for the assessment of LM responses. |
| Approach: | They investigate whether increasing LMs' "thinking" time through scaling test-time compute can improve an LM's evaluation capability. |
| Outcome: | The proposed reasoning models improve evaluation performance monotonically with the number of reasoning tokens generated, mirroring trends seen in LM reasoning. |
Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances have adapted this paradigm to Multimodal Foundation Models (MFMs), unlocking their potential in multimodal reasoning and generation. |
| Approach: | They propose a taxonomy framework that categorizes existing methodologies into three distinct strategies: sampling-based, feedback-based and search-based approaches. |
| Outcome: | The proposed framework categorizes existing methodologies into three distinct strategies: sampling-based, feedback-based and search-based approaches. |
Efficient Test-Time Scaling via Temporal Reasoning Aggregation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing dynamic early-exit methods rely on single-step confidence signals . existing approaches are unreliable for detecting reasoning convergence in multi-step settings . |
| Approach: | They propose a training-free framework for efficient test-time scaling that determines when to terminate reasoning based on temporal aggregation of multi-step evidence rather than instantaneous signals. |
| Outcome: | Experiments show that TRACE reduces reasoning token usage by 25% on average while maintaining accuracy within 1–2% of full-length reasoning. |
Parallel Test-Time Scaling for Latent Reasoning Models (2026.acl-long)
Copied to clipboard
| Challenge: | Parallel test-time scaling is a pivotal approach for enhancing large language models. |
| Approach: | They propose two uncertainty-inspired stochastic strategies for parallel test-time scaling for latent reasoning models and a Latent Reward Model for aggregation. |
| Outcome: | The proposed model scales well with compute and enables effective trajectory selection. |
ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Large Reasoning Models (LRMs) have demonstrated remarkable capabilities across various tasks. |
| Approach: | They propose a system that stops reasoning when the margin between continuation token and lt;/think gt; narrows. |
| Outcome: | The proposed model reduces thinking token usage by 30% and improves accuracy by 8% while reducing thinking tokens by 72%. |
DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have emerged as prominent foundation models for diverse applications due to their outstanding ability to understand and generate humanlike text. |
| Approach: | They propose a dynamic decision-making framework that categorizes tasks into two distinct pathways: 'Fast' and 'Slow' they propose 'self-consistency' strategy to replace the straight-forward decoding method used in COT prompting . |
| Outcome: | The proposed method achieves more than 3% increase in accuracy with lower cost on five popular reasoning benchmarks. |
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. |