中文
相关论文

相关论文: HER: Human-like Reasoning and Reinforcement Learni…

200 篇论文

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…

The use of LLMs in natural language reasoning has shown mixed results, sometimes rivaling or even surpassing human performance in simpler classification tasks while struggling with social-cognitive reasoning, a domain where humans naturally…

Reinforcement Learning (RL) has been shown to improve the capabilities of large language models (LLMs). However, applying RL to open-domain tasks faces two key challenges: (1) the inherent subjectivity of these tasks prevents the verifiable…

机器学习 · 计算机科学 2026-02-26 Weixuan Ou , Yanzhao Zheng , Shuoshuo Sun , Wei Zhang , Baohua Dong , Hangcheng Zhu , Ruohui Huang , Gang Yu , Pengwei Yan , Yifan Qiao

Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where…

机器学习 · 计算机科学 2020-05-28 Yiming Ding , Carlos Florensa , Mariano Phielipp , Pieter Abbeel

Simulating user search behavior is a critical task in information retrieval, which can be employed for user behavior modeling, data augmentation, and system evaluation. Recent advancements in large language models (LLMs) have opened up new…

信息检索 · 计算机科学 2025-04-11 Erhan Zhang , Xingzhu Wang , Peiyuan Gong , Zixuan Yang , Jiaxin Mao

Contemporary progress in large language models (LLMs) has revealed notable inferential capacities via reinforcement learning (RL) employing verifiable reward, facilitating the development of O1 and R1-like reasoning models. Directly…

机器学习 · 计算机科学 2025-10-21 Zexu Sun , Yongcheng Zeng , Erxue Min , Heyang Gao , Bokai Ji , Xu Chen

Improving the multi-step reasoning ability of Large Language Models (LLMs) is a critical yet challenging task. The dominant paradigm, outcome-supervised reinforcement learning (RLVR), rewards only correct final answers, often propagating…

人工智能 · 计算机科学 2025-10-14 Beining Wang , Weihang Su , Hongtao Tian , Tao Yang , Yujia Zhou , Ting Yao , Qingyao Ai , Yiqun Liu

This paper delves into the dynamic landscape of artificial intelligence, specifically focusing on the burgeoning prominence of large language models (LLMs). We underscore the pivotal role of Reinforcement Learning from Human Feedback (RLHF)…

计算机与社会 · 计算机科学 2024-03-18 Dana Alsagheer , Rabimba Karanjai , Nour Diallo , Weidong Shi , Yang Lu , Suha Beydoun , Qiaoning Zhang

Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and delayed rewards, where agents must execute extended sequences of actions before receiving meaningful…

机器学习 · 计算机科学 2026-05-12 Jiangweizhi Peng , Yuanxin Liu , Ruida Zhou , Charles Fleming , Zhaoran Wang , Alfredo Garcia , Mingyi Hong

Current LLM post-training methods optimize complete reasoning trajectories through Supervised Fine-Tuning (SFT) followed by outcome-based Reinforcement Learning (RL). While effective, a closer examination reveals a fundamental gap: this…

人工智能 · 计算机科学 2026-05-29 Shaojie Wang , Liang Zhang

Recent large reasoning models (LRMs) have demonstrated strong reasoning capabilities through reinforcement learning (RL). These improvements have primarily been observed within the short-context reasoning tasks. In contrast, extending LRMs…

计算与语言 · 计算机科学 2025-05-28 Fanqi Wan , Weizhou Shen , Shengyi Liao , Yingcheng Shi , Chenliang Li , Ziyi Yang , Ji Zhang , Fei Huang , Jingren Zhou , Ming Yan

Reinforcement Learning (RL) has emerged as a transformative approach for aligning and enhancing Large Language Models (LLMs), addressing critical challenges in instruction following, ethical alignment, and reasoning capabilities. This…

人工智能 · 计算机科学 2025-07-08 Saksham Sahai Srivastava , Vaneet Aggarwal

The rapid rise of large language models (LLMs) has shifted artificial intelligence (AI) research toward agentic systems, motivating the use of weaker and more flexible notions of agency. However, this shift raises key questions about the…

人工智能 · 计算机科学 2025-10-27 Vince Trencsenyi , Agnieszka Mensfelt , Kostas Stathis

Progress in long-context reasoning for large language models (LLMs) has lagged behind other recent advances. This gap arises not only from the intrinsic difficulty of processing long texts, but also from the scarcity of reliable human…

计算与语言 · 计算机科学 2026-03-16 Ziyi Yang , Weizhou Shen , Chenliang Li , Ruijun Chen , Fanqi Wan , Ming Yan , Xiaojun Quan , Fei Huang

Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However,…

人工智能 · 计算机科学 2025-11-12 Qianxi He , Qingyu Ren , Shanzhe Lei , Xuhong Wang , Yingchun Wang

Large Language Models (LLMs) have shown promise in character imitation, enabling immersive and engaging conversations. However, they often generate content that is irrelevant or inconsistent with a character's background. We attribute these…

人工智能 · 计算机科学 2025-05-27 Yongjie Wang , Jonathan Leung , Zhiqi Shen

Learning optimal policies from sparse feedback is a known challenge in reinforcement learning. Hindsight Experience Replay (HER) is a multi-goal reinforcement learning algorithm that comes to solve such tasks. The algorithm treats every…

机器学习 · 计算机科学 2020-01-14 Binyamin Manela

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for enhancing reasoning in Large Language Models (LLMs). However, existing reward formulations typically treat exploration and consolidation as a…

机器学习 · 计算机科学 2026-05-15 Wenze Lin , Zhen Yang , Xitai Jiang , Xiaoteng Ma , Gao Huang

The growing scale of evaluation tasks has led to the widespread adoption of automated evaluation using LLMs, a paradigm known as "LLM-as-a-judge". However, improving its alignment with human preferences without complex prompts or…

计算与语言 · 计算机科学 2025-10-17 Peng Lai , Jianjie Zheng , Sijie Cheng , Yun Chen , Peng Li , Yang Liu , Guanhua Chen

Reverse thinking plays a crucial role in human reasoning. Humans can reason not only from a problem to a solution but also in reverse, i.e., start from the solution and reason towards the problem. This often enhances overall reasoning…