English
Related papers

Related papers: RubricRefine: Improving Tool-Use Agent Reliability…

200 papers

Despite recent progress in Large Language Model (LLM) Agents for Software Engineering (SWE) tasks, end-to-end fine-tuning typically relies on verifiable terminal rewards such as whether all unit tests pass. While these binary signals…

Machine Learning · Computer Science 2026-04-21 Jiawei Huang , Qingping Yang , Renjie Zheng , Jiaze Chen

Recent advances in long chain-of-thought (CoT) reasoning have largely prioritized answer accuracy and token efficiency, while overlooking aspects critical to trustworthiness. We argue that usable reasoning systems must be trustworthy,…

Computation and Language · Computer Science 2025-10-13 Chung-En Sun , Ge Yan , Akshay Kulkarni , Tsui-Wei Weng

Standard reward models typically predict scalar scores that fail to capture the multifaceted nature of response quality in non-verifiable domains, such as creative writing or open-ended instruction following. To address this limitation, we…

Computation and Language · Computer Science 2026-02-13 Ran Xu , Tianci Liu , Zihan Dong , Tony Yu , Ilgee Hong , Carl Yang , Linjun Zhang , Tao Zhao , Haoyu Wang

Recent advancements in Large Language Models (LLMs) have significantly improved reasoning capabilities, with in-context learning (ICL) emerging as a key technique for adaptation without retraining. While previous works have focused on…

Machine Learning · Computer Science 2025-12-17 Jongyeop Hyun , Bumsoo Kim

He et al. (2018) have called into question the utility of pre-training by showing that training from scratch can often yield similar performance to pre-training. We show that although pre-training may not improve performance on traditional…

Machine Learning · Computer Science 2019-10-22 Dan Hendrycks , Kimin Lee , Mantas Mazeika

We propose a framework that amortizes the cost of inference-time reasoning by converting transient critiques into retrievable guidelines, through a file-based memory system and agent-controlled tool calls. We evaluate this method on the…

Computation and Language · Computer Science 2026-03-19 Víctor Gallego

Open-ended generation tasks require outputs to satisfy diverse and often implicit task-specific evaluation rubrics. The sheer number of relevant rubrics leads to prohibitively high verification costs and incomplete assessments of a…

Machine Learning · Computer Science 2025-11-04 Mian Wu , Gavin Zhang , Sewon Min , Sergey Levine , Aviral Kumar

Recently, rubrics have been used to guide LLM judges in capturing subjective, nuanced, multi-dimensional human preferences, and have been extended from evaluation to reward signals for reinforcement fine-tuning (RFT). However, rubric…

Reinforcement learning post-training has substantially improved the reasoning accuracy of vision-language models, yet the resulting policies remain poorly calibrated. Terminal correctness rewards provide no gradient that penalizes confident…

Machine Learning · Computer Science 2026-05-19 Peng Cui , Boyao Yang , Jun Zhu

Large Language Models (LLMs) often rely on test-time scaling via parallel decoding (for example, 512 samples) to boost reasoning accuracy, but this incurs substantial compute. We introduce CoRefine, a confidence-guided self-refinement…

Artificial Intelligence · Computer Science 2026-02-10 Chen Jin , Ryutaro Tanno , Tom Diethe , Philip Teare

Reinforcement learning (RL) training of large language models (LLMs) on unverifiable tasks is challenging even when a reasonable-quality reference answer is available. We propose a constrained RL training framework that (i) optimizes a…

Most prompt-optimization methods refine a single static template, making them ineffective in complex and dynamic user scenarios. Existing query-dependent approaches rely on unstable textual feedback or black-box reward models, providing…

Artificial Intelligence · Computer Science 2025-11-26 Ke Chen , Yifeng Wang , Hassan Almosapeeh , Haohan Wang

Rubric-based text evaluation increasingly uses large language models (LLMs) as scalable judges, but aligning frozen black-box models with human scoring standards remains challenging. We formulate this challenge as a criteria-transfer…

Computation and Language · Computer Science 2026-05-29 Yihan Hong , Huaiyuan Yao , Bolin Shen , Wanpeng Xu , Hua Wei , Yushun Dong

The performance of Large Language Models (LLMs) on downstream tasks is fundamentally constrained by the capabilities acquired during pre-training. However, traditional benchmarks like MMLU often fail to reflect a base model's plasticity in…

Computation and Language · Computer Science 2026-05-13 Xiaoyuan Li , Yubo Ma , Kexin Yang , Moxin Li , Keqin Bao , Wenie Wang , Fuli Feng , Dayiheng Liu

Rubric-augmented verification guides reward models with explicit evaluation criteria, yielding more reliable judgments than single-model verification. However, most existing methods require costly rubric annotations, limiting scalability.…

Computation and Language · Computer Science 2026-04-16 Akira Kawabata , Saku Sugawara

Recent large language models (LLM) are leveraging human feedback to improve their generation quality. However, human feedback is costly to obtain, especially during inference. In this work, we propose LLMRefine, an inference time…

Computation and Language · Computer Science 2024-10-28 Wenda Xu , Daniel Deutsch , Mara Finkelstein , Juraj Juraska , Biao Zhang , Zhongtao Liu , William Yang Wang , Lei Li , Markus Freitag

ReAct-style agents for search-intensive, multi-step reasoning tasks rely largely on their own internal judgment to decide what evidence to seek, which reasoning or action step to take next, and when to stop, often producing shallow,…

Artificial Intelligence · Computer Science 2026-05-25 Jiazheng Kang , Bowen Zhang , Zixin Song , Jiangwang Chen , Xiao Yang , Da Zhu , Guanjun Jiang

Visual programming, a modular and generalizable paradigm, integrates different modules and Python operators to solve various vision-language tasks. Unlike end-to-end models that need task-specific data, it advances in performing visual…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Minghe Gao , Juncheng Li , Hao Fei , Liang Pang , Wei Ji , Guoming Wang , Zheqi Lv , Wenqiao Zhang , Siliang Tang , Yueting Zhuang

Generating natural language explanations for recommendations has become increasingly important in recommender systems. Traditional approaches typically treat user reviews as ground truth for explanations and focus on improving review…

Information Retrieval · Computer Science 2025-02-18 Jingsen Zhang , Zihang Tian , Xueyang Feng , Xu Chen

Small language models (1-3B) are practical to run locally, but individually limited on harder code generation tasks. We ask whether composing them into pipelines can recover some of that lost capability. We study code generation pipelines…

Software Engineering · Computer Science 2026-04-27 Charles Junichi McAndrews