English
Related papers

Related papers: Reward Model Generalization for Compute-Aware Test…

200 papers

Social biases inherent in large language models (LLMs) raise significant fairness concerns. Retrieval-Augmented Generation (RAG) architectures, which retrieve external knowledge sources to enhance the generative capabilities of LLMs, remain…

Computation and Language · Computer Science 2026-02-11 Shweta Parihar , Lu Cheng

Large multimodal reasoning models have achieved rapid progress, but their advancement is constrained by two major limitations: the absence of open, large-scale, high-quality long chain-of-thought (CoT) data, and the instability of…

Computer Vision and Pattern Recognition · Computer Science 2025-09-26 Sicong Leng , Jing Wang , Jiaxi Li , Hao Zhang , Zhiqiang Hu , Boqiang Zhang , Yuming Jiang , Hang Zhang , Xin Li , Lidong Bing , Deli Zhao , Wei Lu , Yu Rong , Aixin Sun , Shijian Lu

Reinforcement learning (RL) for large language models (LLMs) increasingly relies on sparse, outcome-level rewards -- yet determining which actions within a long trajectory caused the outcome remains difficult. This credit assignment (CA)…

Computation and Language · Computer Science 2026-04-14 Chenchen Zhang

Reward models (RMs) play a critical role in aligning language models through the process of reinforcement learning from human feedback. RMs are trained to predict a score reflecting human preference, which requires significant time and cost…

Computation and Language · Computer Science 2024-10-21 Zihuiwen Ye , Fraser Greenlee-Scott , Max Bartolo , Phil Blunsom , Jon Ander Campos , Matthias Gallé

Chain-of-thought (CoT) reasoning has become the standard paradigm for enabling Large Language Models (LLMs) to solve complex problems. However, recent studies reveal a sharp performance drop in reasoning hop generalization scenarios, where…

Computation and Language · Computer Science 2026-05-04 Zhaoyi Li , Jiatong Li , Gangwei Jiang , Linqi Song , Defu Lian , Ying Wei

Large Language Models excel at code generation yet struggle with complex programming tasks that demand sophisticated reasoning. To bridge this gap, traditional process supervision relies on learned reward models requiring costly training…

Computation and Language · Computer Science 2025-06-09 Zhuohao Yu , Weizheng Gu , Yidong Wang , Xingru Jiang , Zhengran Zeng , Jindong Wang , Wei Ye , Shikun Zhang

Large language models (LLMs) have shown remarkable reasoning capabilities, especially when prompted to generate intermediate reasoning steps (e.g., Chain-of-Thought, CoT). However, LLMs can still struggle with problems that are easy for…

Computation and Language · Computer Science 2023-10-24 Shibo Hao , Yi Gu , Haodi Ma , Joshua Jiahua Hong , Zhen Wang , Daisy Zhe Wang , Zhiting Hu

Tree search has become as a representative framework for test-time reasoning with large language models (LLMs), exemplified by methods such as Tree-of-Thought and Monte Carlo Tree Search. However, it remains difficult to provide instant and…

Artificial Intelligence · Computer Science 2026-03-02 Jiaxi Li , Yucheng Shi , Xiao Huang , Jin Lu , Ninghao Liu

Large language models (LLMs) have rapidly progressed into general-purpose agents capable of solving a broad spectrum of tasks. However, current models remain inefficient at reasoning: they apply fixed inference-time compute regardless of…

Reinforcement Learning with Verifiable Rewards (RLVR) improves final-answer accuracy on reasoning tasks, but it does not reliably improve reasoning quality. Because outcome rewards only assess final answers, they also reward spurious…

Machine Learning · Computer Science 2026-05-19 Chenlu Ye , Zhou Yu , Ziji Zhang , Hao Chen , Narayanan Sadagopan , Jing Huang , Tong Zhang , Anurag Beniwal

Large Language Models have excelled in remarkable reasoning capabilities with advanced prompting techniques, but they fall short on tasks that require exploration, strategic foresight, and sequential decision-making. Recent works propose to…

Computation and Language · Computer Science 2023-10-18 Zheyu Zhang , Zhuorui Ye , Yikang Shen , Chuang Gan

Information-seeking is a core capability for AI agents, requiring them to gather and reason over tool-generated information across long trajectories. However, such multi-step information-seeking tasks remain challenging for agents backed by…

Artificial Intelligence · Computer Science 2025-11-25 Jaewoo Lee , Archiki Prasad , Justin Chih-Yao Chen , Zaid Khan , Elias Stengel-Eskin , Mohit Bansal

Designing effective auxiliary rewards for cooperative multi-agent systems remains challenging, as misaligned incentives can induce suboptimal coordination, particularly when sparse task rewards provide insufficient grounding for coordinated…

Machine Learning · Computer Science 2026-04-07 Dogan Urgun , Gokhan Gungor

Large Language Models (LLMs) exhibit remarkable proficiency in addressing a diverse array of tasks within the Natural Language Processing (NLP) domain, with various prompt design strategies significantly augmenting their capabilities.…

Computation and Language · Computer Science 2024-08-05 Xiangyu Zhao , Chengqian Ma

Test-time computation has become a primary driver of progress in large language model (LLM) reasoning, but it is increasingly bottlenecked by expensive verification. In many reasoning systems, a large fraction of verifier calls are spent on…

Artificial Intelligence · Computer Science 2026-02-05 Shuhui Qu

Large reasoning models (LRMs) have achieved remarkable progress in complex problem-solving tasks. Despite this success, LRMs typically suffer from high computational costs during deployment, highlighting a need for efficient inference. A…

Artificial Intelligence · Computer Science 2026-02-02 Hao Zeng , Jianguo Huang , Bingyi Jing , Hongxin Wei , Bo An

Despite their outstanding capabilities, large language models (LLMs) are prone to hallucination and producing factually incorrect information. This challenge has spurred efforts in attributed text generation, which prompts LLMs to generate…

Computation and Language · Computer Science 2025-06-23 Junyi Li , Hwee Tou Ng

Reinforcement learning (RL) has significantly improved the reasoning ability of large language models. However, current reward models underperform in challenging reasoning scenarios and predominant RL training paradigms rely on rule-based…

Computation and Language · Computer Science 2025-07-30 Meng Zhou , Bei Li , Jiahao Liu , Xiaowen Shi , Yang Bai , Rongxiang Weng , Jingang Wang , Xunliang Cai

Large Language Models (LLMs) are demonstrating rapid improvements on complex reasoning benchmarks, particularly when allowed to utilize intermediate reasoning steps before converging on a final solution. However, current literature often…

Computation and Language · Computer Science 2026-01-01 Ákos Prucs , Márton Csutora , Mátyás Antal , Márk Marosi

Large pretrained models are showing increasingly better performance in reasoning and planning tasks across different modalities, opening the possibility to leverage them for complex sequential decision making problems. In this paper, we…

Artificial Intelligence · Computer Science 2024-10-10 Martin Klissarov , Devon Hjelm , Alexander Toshev , Bogdan Mazoure