The paper introduces TASCO, a test‑time adaptation framework that enhances Large Language Model reasoning by incorporating local stability into confidence‑based adaptation while keeping the model frozen. TASCO optimizes a lightweight task‑level prefix using two perturbation strategies—Random Perturbation for distributional stability and Sharpness‑Aware Perturbation for worst‑case sensitivity—to ensure that high confidence aligns with correctness. Experiments show that TASCO improves reasoning accuracy and token efficiency across various LLMs and benchmarks, and behavioral analyses confirm that it maintains stable confidence without over‑concentrating the predictive distribution.
By Bincheng Gu, Min Gao, Zongwei Wang, Yibing Bai, Yulan He, Junliang Yu
arXiv:2510. 13940v4 Announce Type: replace-cross Abstract: Recent progress in large language models (LLMs) has focused on test-time scaling to improve reasoning via increased inference computation, but often at the cost of efficiency.
By Zhen Yang, Mingyang Zhang, Feng Chen, Ganggui Ding, Liang Hou, Xin Tao, Ying-Cong Chen
The paper investigates how trajectory-based confidence estimation for large language models deteriorates after agentic reinforcement learning (Agentic RL) due to shifts in reasoning trajectories. It discovers that more stable trajectories consistently correlate with correct answers, a relationship that remains intact across both base and RL models. Leveraging this insight, the authors introduce StaR-TTA, a stability-guided test-time confidence adaptation framework that learns from labeled base trajectories and applies stability-derived reliability rankings to unlabeled RL trajectories, achieving improved AUROC scores across multiple QA benchmarks.
By Zhenzhen Ren, Xiaoqing Zhang, GuoBiao Li, Bowen Fang, Yanxi Wang, Xinpeng Zhang, Ke Han
The paper introduces Test-Time Calibration Learning (TTCL), a label‑free framework that adapts both reasoning accuracy and verbalized confidence of large language models directly on unlabeled target‑task data. TTCL generates self‑supervision signals from multiple model responses, enabling calibration without ground‑truth labels and proving theoretically as a bounded surrogate for the ideal calibration objective. Experiments on mathematical reasoning and factual question answering show consistent improvements, with base models gaining an average 40.13% in accuracy and 70.80% in ECE reduction across eight benchmarks, and further gains under domain shift.
By Zizhuo Zhang, Xiong Peng, Jingwei Sun, Rong Yao, Shixiong Kai, Mingxuan Yuan, Bo Han
arXiv:2601.19847v3 Announce Type: replace
Abstract: Despite the strong reasoning capabilities of recent large language models (LLMs), achieving reliable performance on challenging tasks often require...
By Fangan Dong, Zuming Yan, Xuri Ge, Zhiwei Xu, Mengqi Zhang, Xuanang Chen, Ben He, Xin Xin, Zhumin Chen, Ying Zhou
RL-ARC introduces a calibration-aware training framework that uses reasoning confidence to guide the calibration of answer confidence in large reasoning models. By applying reasoning-guided regularization for correct predictions and an overconfidence penalty for incorrect ones, RL-ARC improves calibration across both in-distribution and out-of-distribution settings. The approach maintains reasoning performance while enabling models to adaptively estimate confidence for each question.
arXiv:2604. 23333v2 Announce Type: replace Abstract: Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability.
By Liaoyaqi Wang, Chunsheng Zuo, William Jurayj, Benjamin Van Durme, Anqi Liu
arXiv:2606. 03608v1 Announce Type: cross Abstract: Test-time reinforcement learning has emerged as a promising paradigm for enhancing the complex reasoning abilities of large language models in a completely label-free manner.
By Jiahui Li, Jianfeng Shan, Wenpei Chen, Shunyu Wu, Jian Lou, Wenjie Feng, Dan Li, See-Kiong Ng
RL-ARC is a calibration‑aware training framework that jointly uses reasoning confidence and answer confidence to improve the calibration of large reasoning models. It applies reasoning‑guided regularization for correct predictions and an overconfidence penalty for incorrect ones. Experiments on in‑distribution and out‑of‑distribution data show that RL‑ARC enhances calibration while preserving reasoning performance.
By Gukhyeon Lee, SangKeun Lee
arXiv:2607. 00862v1 Announce Type: cross Abstract: Large Reasoning Models (LRMs) have achieved remarkable success on complex tasks by leveraging long chain-of-thought (CoT) trajectories, yet they frequently exhibit overthinking on simple queries, resulting in significant token overhead and reduced inference efficiency.
By Qizhi Jiang, Shuo Wang, Pei Ke, Yuhang Song, Ke Qin
arXiv:2608. 09898v1 Announce Type: cross Abstract: Test-time scaling often uses an external verifier, such as compilers and test cases in coding or trained value functions in robotics applications, to obtain high-quality rollouts.
By Lecheng Kong, Like Hui, Haitao Mao, Jun Huan
arXiv:2507.21931v2 Announce Type: replace-cross
Abstract: Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks....
By Carel van Niekerk, Renato Vukovic, Benjamin Ruppik, Hsien-chin Lin, Shutong Feng, Milica Ga\v{s}i\'c