The paper introduces TASCO, a test‑time adaptation method that improves Large Language Model reasoning by optimizing stability‑aware confidence. It keeps the LLM frozen and uses a lightweight task‑level prefix, applying Random Perturbation for distributional stability and Sharpness‑Aware Perturbation for worst‑case sensitivity. Experiments show enhanced reasoning accuracy and token efficiency across various LLMs and benchmarks, while preserving stable confidence without over‑concentrating predictions.
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:2607. 07626v1 Announce Type: cross Abstract: Reliable confidence estimation is essential for deploying large language models (LLMs) in confidence-aware systems, where downstream decisions such as retrieval, tool use, and adaptive computation depend on accurately estimating answer reliability.
By Sahil Kale
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
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
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:2604.08974v2 Announce Type: replace
Abstract: Uncertainty quantification techniques measure confidence in language model outputs to support critical applications like hallucination detection an...
By Lorenzo Jaime Yu Flores, Cesare Spinoso di-Piano, Jackie Chi Kit Cheung
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
arXiv:2605. 24396v2 Announce Type: replace Abstract: Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute.
By Jingchu Gai, Guanning Zeng, Christina Baek, Chen Wu, J. Zico Kolter, Andrej Risteski, Aditi Raghunathan
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.