English
Related papers

Related papers: Furthest Reasoning with Plan Assessment: Stable Re…

200 papers

Efficient multi-hop reasoning requires Large Language Models (LLMs) based agents to acquire high-value external knowledge iteratively. Previous work has explored reinforcement learning (RL) to train LLMs to perform search-based document…

Computation and Language · Computer Science 2025-05-27 Ziliang Wang , Xuhui Zheng , Kang An , Cijun Ouyang , Jialu Cai , Yuhang Wang , Yichao Wu

Large language model (LLM)-based agents exhibit strong step-by-step reasoning capabilities over short horizons, yet often fail to sustain coherent behavior over long planning horizons. We argue that this failure reflects a fundamental…

Artificial Intelligence · Computer Science 2026-02-02 Zehong Wang , Fang Wu , Hongru Wang , Xiangru Tang , Bolian Li , Zhenfei Yin , Yijun Ma , Yiyang Li , Weixiang Sun , Xiusi Chen , Yanfang Ye

Reinforcement Learning (RL) has emerged as the key driver for post-training complex reasoning in Large Language Models (LLMs), yet online RL introduces significant instability and computational overhead. Offline RL offers a compelling…

Computation and Language · Computer Science 2026-04-06 Minjae Oh , Yunho Choi , Dongmin Choi , Yohan Jo

Retrieval-Augmented Generation (RAG) effectively enhances Large Language Models (LLMs) by incorporating retrieved external knowledge into the generation process. Reasoning models improve LLM performance in multi-hop QA tasks, which require…

Computation and Language · Computer Science 2026-01-21 Guo Chen , Junjie Huang , Huaijin Xie , Fei Sun , Tao Jia

Multi-Hop Question Answering (MHQA) requires integrating dispersed, interdependent evidence through sequential reasoning under noise. This task is challenging for LLMs as they have a finite per-pass output capacity, beyond which the…

Artificial Intelligence · Computer Science 2026-04-28 Kaiyang Wan , Lang Gao , Honglin Mu , Preslav Nakov , Yuxia Wang , Xiuying Chen

Evaluating generative models, such as large language models (LLMs), commonly involves question-answering tasks where the final answer is selected based on probability of answer choices. On the other hand, for models requiring reasoning, the…

Computation and Language · Computer Science 2025-10-17 Hwiyeol Jo , Joosung Lee , Jaehone Lee , Sang-Woo Lee , Joonsuk Park , Kang Min Yoo

We present a novel framework addressing a critical vulnerability in Large Language Models (LLMs): the prevalence of factual inaccuracies within intermediate reasoning steps despite correct final answers. This phenomenon poses substantial…

Computation and Language · Computer Science 2025-08-05 Rui Jiao , Yue Zhang , Jinku Li

The ability to perform multi-modal multi-hop reasoning by iteratively integrating information across various modalities and external knowledge is critical for addressing complex real-world challenges. However, existing Multi-modal Large…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Tao Zhang , Ziqi Zhang , Zongyang Ma , Yuxin Chen , Bing Li , Chunfeng Yuan , Guangting Wang , Fengyun Rao , Ying Shan , Weiming Hu

We present MA-RAG, a Multi-Agent framework for Retrieval-Augmented Generation (RAG) that addresses the inherent ambiguities and reasoning challenges in complex information-seeking tasks. Unlike conventional RAG methods that rely on…

Computation and Language · Computer Science 2025-10-14 Thang Nguyen , Peter Chin , Yu-Wing Tai

Tree-search-based reasoning methods have significantly enhanced the reasoning capability of large language models (LLMs) by facilitating the exploration of multiple intermediate reasoning steps, i.e., thoughts. However, these methods suffer…

Computation and Language · Computer Science 2025-05-27 Zhihai Wang , Jie Wang , Jilai Pan , Xilin Xia , Huiling Zhen , Mingxuan Yuan , Jianye Hao , Feng Wu

The Mental Health Question Answer (MHQA) task requires the seeker and supporter to complete the support process in one-turn dialogue. Given the richness of help-seeker posts, supporters must thoroughly understand the content and provide…

Computation and Language · Computer Science 2025-01-28 Qi Chen , Dexi Liu

In this paper, we introduce a method for fine-tuning Large Language Models (LLMs), inspired by Multi-Task learning in a federated manner. Our approach leverages the structure of each client's model and enables a learning scheme that…

Machine Learning · Computer Science 2024-10-22 Ahmed Elbakary , Chaouki Ben Issaid , Tamer ElBatt , Karim Seddik , Mehdi Bennis

Multimodal large language models (MLLMs) have shown promising capabilities in reasoning tasks, yet still struggle with complex problems requiring explicit self-reflection and self-correction, especially compared to their unimodal text-based…

Computation and Language · Computer Science 2025-10-07 Zhongwei Wan , Zhihao Dou , Che Liu , Yu Zhang , Dongfei Cui , Qinjian Zhao , Hui Shen , Jing Xiong , Yi Xin , Yifan Jiang , Chaofan Tao , Yangfan He , Mi Zhang , Shen Yan

Modern Question Answering (QA) and Reasoning approaches based on Large Language Models (LLMs) commonly use prompting techniques, such as Chain-of-Thought (CoT), assuming the resulting generation will have a more granular exploration and…

Artificial Intelligence · Computer Science 2025-09-22 Erik Arakelyan , Pasquale Minervini , Pat Verga , Patrick Lewis , Isabelle Augenstein

Prompting-based large language models (LLMs) are surprisingly powerful at generating natural language reasoning steps or Chains-of-Thoughts (CoT) for multi-step question answering (QA). They struggle, however, when the necessary knowledge…

Computation and Language · Computer Science 2023-06-26 Harsh Trivedi , Niranjan Balasubramanian , Tushar Khot , Ashish Sabharwal

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge. Current hybrid RAG system retrieves evidence from both knowledge graphs (KGs) and text documents to support LLM reasoning.…

Computation and Language · Computer Science 2025-09-22 Xingyu Tan , Xiaoyang Wang , Qing Liu , Xiwei Xu , Xin Yuan , Liming Zhu , Wenjie Zhang

Reinforcement Learning (RL) has proven highly effective at enhancing the complex reasoning abilities of Large Language Models (LLMs), yet underlying mechanisms driving this success remain largely opaque. Our analysis reveals that puzzling…

Artificial Intelligence · Computer Science 2025-09-30 Haozhe Wang , Qixin Xu , Che Liu , Junhong Wu , Fangzhen Lin , Wenhu Chen

Despite the significant progress of large language models (LLMs) in various tasks, they often produce factual errors due to their limited internal knowledge. Retrieval-Augmented Generation (RAG), which enhances LLMs with external knowledge…

Computation and Language · Computer Science 2024-10-10 Yuanjie Lyu , Zihan Niu , Zheyong Xie , Chao Zhang , Tong Xu , Yang Wang , Enhong Chen

Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with knowledge-intensive reasoning tasks, because useful…

Computation and Language · Computer Science 2024-10-28 Zhuoqun Li , Xuanang Chen , Haiyang Yu , Hongyu Lin , Yaojie Lu , Qiaoyu Tang , Fei Huang , Xianpei Han , Le Sun , Yongbin Li

Large Language Models (LLMs) often struggle with complex multi-step planning tasks, showing high rates of constraint violations and inconsistent solutions. Existing strategies such as Chain-of-Thought and ReAct rely on implicit state…

Artificial Intelligence · Computer Science 2025-12-17 Annu Rana , Gaurav Kumar