中文
相关论文

相关论文: HS-STaR: Hierarchical Sampling for Self-Taught Rea…

200 篇论文

The proliferation of Large Language Models (LLMs) in function calling is pivotal for creating advanced AI agents, yet their large scale hinders widespread adoption, necessitating transferring their capabilities into smaller ones. However,…

人工智能 · 计算机科学 2026-02-25 Jiliang Ni , Jiachen Pu , Zhongyi Yang , Jingfeng Luo , Conggang Hu

We study self-rewarding reasoning large language models (LLMs), which can simultaneously generate step-by-step reasoning and evaluate the correctness of their outputs during the inference time-without external feedback. This integrated…

人工智能 · 计算机科学 2025-02-28 Wei Xiong , Hanning Zhang , Chenlu Ye , Lichang Chen , Nan Jiang , Tong Zhang

Large Language Models (LLMs) have demonstrated remarkable capabilities in various reasoning-intensive tasks. However, these models exhibit unexpected brittleness, often failing on simple variations of the same underlying task. Existing…

计算与语言 · 计算机科学 2026-04-27 Yutao Hou , Zeguan Xiao , Fei Yu , Yihan Jiang , Ma Shuguang , Zhaoqian Dai , Hailiang Huang , Yun Chen , Guanhua Chen

Large language models (LLMs) exhibit strong reasoning capabilities but typically require expensive post-training to reach high performance. Recent test-time alignment methods offer a lightweight alternative, but have been explored mainly…

计算与语言 · 计算机科学 2026-03-20 Arushi Rai , Qiang Zhang , Hanqing Zeng , Yunkai Zhang , Dipesh Tamboli , Xiangjun Fan , Zhuokai Zhao , Lizhu Zhang

Large language models (LLMs) are increasingly expected to tackle complex tasks, driven by their expanding applications and users' growing proficiency in crafting sophisticated prompts. However, as the number of explicitly stated…

Reinforcement Learning (RL) has made significant strides in enabling artificial agents to learn diverse behaviors. However, learning an effective policy often requires a large number of environment interactions. To mitigate sample…

人工智能 · 计算机科学 2024-04-04 Yash Shukla , Tanushree Burman , Abhishek Kulkarni , Robert Wright , Alvaro Velasquez , Jivko Sinapov

Large Language Models (LLMs) have exhibited an impressive capability to perform reasoning tasks, especially if they are encouraged to generate a sequence of intermediate steps. Reasoning performance can be improved by suitably combining…

计算与语言 · 计算机科学 2025-04-11 Soumyasundar Pal , Didier Chételat , Yingxue Zhang , Mark Coates

The alignments of reasoning abilities between smaller and larger Language Models are largely conducted via Supervised Fine-Tuning (SFT) using demonstrations generated from robust Large Language Models (LLMs). Although these approaches…

计算与语言 · 计算机科学 2025-01-28 Leonardo Ranaldi , Andrè Freitas

Large Language Models have demonstrated outstanding performance across various downstream tasks and have been widely applied in multiple scenarios. Human-annotated preference data is used for training to further improve LLMs' performance,…

计算与语言 · 计算机科学 2025-03-06 Shimao Zhang , Xiao Liu , Xin Zhang , Junxiao Liu , Zheheng Luo , Shujian Huang , Yeyun Gong

Test-time scaling methods have seen a rapid increase in popularity for its computational efficiency and parameter-independent training to improve reasoning performance on Large Language Models. One such method is called budget forcing, a…

人工智能 · 计算机科学 2025-10-27 Ravindra Aribowo Tarunokusumo , Rafael Fernandes Cunha

External test-time reasoning enhances large language models (LLMs) by decoupling generation and selection. At inference time, the model generates multiple reasoning paths, and an auxiliary process reward model (PRM) is used to score and…

机器学习 · 计算机科学 2025-05-26 Zeen Song , Wenwen Qiang , Siyu Zhao , Changwen Zheng , Gang Hua

This paper investigates the capabilities of large language models (LLMs) in formulating and solving decision-making problems using mathematical programming. We first conduct a systematic review and meta-analysis of recent literature to…

Large reasoning models (LRMs) achieve state-of-the-art performance by generating long chains-of-thought, but often waste computation on redundant reasoning after the correct answer has already been reached. We introduce Early-Stopping for…

人工智能 · 计算机科学 2026-02-11 Junda Wang , Zhichao Yang , Dongxu Zhang , Sanjit Singh Batra , Robert E. Tillman

Recent analyses question whether reinforcement learning (RL) is responsible for strong reasoning in large language models (LLMs). At the same time, distillation and inference-time sampling, including power sampling, have emerged as…

机器学习 · 计算机科学 2026-05-07 Akiyoshi Tomihari , Issei Sato

Reinforcement Learning with Verifiable Reward (RLVR) is empirically shown to notably enhance the reasoning performance of large language models (LLMs), particularly in mathematics and programming. However, the mechanistic role of Sample…

人工智能 · 计算机科学 2026-05-28 Yue Cheng , Jiajun Zhang , Xiaohui Gao , Weiwei Xing , Zheng Wang , Zhanxing Zhu

Specialized reasoning language models (RLMs) have demonstrated that scaling test-time computation through detailed reasoning traces significantly enhances performance. Although these traces effectively facilitate knowledge distillation into…

计算与语言 · 计算机科学 2025-07-16 Philip Lippmann , Jie Yang

Reasoning-capable large language models (LLMs) have recently been adopted as automated judges, but their benefits and costs in LLM-as-a-Judge settings remain unclear. Through controlled comparisons between reasoning and non-reasoning…

人工智能 · 计算机科学 2026-05-12 Wenbo Zhang , Lijinghua Zhang , Liner Xiang , Hengrui Cai

Large language models (LLMs) have shown impressive capabilities across a wide range of language tasks. However, their reasoning process is primarily guided by statistical patterns in training data, which limits their ability to handle novel…

人工智能 · 计算机科学 2025-08-21 Hong Su

Small language models (SLMs) often struggle with complex mathematical reasoning due to limited capacity to maintain long chains of intermediate steps and to recover from early errors. We address this challenge by introducing a hint-assisted…

人工智能 · 计算机科学 2026-04-15 Jawad Hossain , Xiangyu Guo , Jiawei Zhou , Chong Liu

Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL). But conventional approaches rely on outcome-only rewards that provide sparse feedback, resulting in…

机器学习 · 计算机科学 2025-08-01 Tao He , Rongchuan Mu , Lizi Liao , Yixin Cao , Ming Liu , Bing Qin