English
Related papers

Related papers: LADDER: Self-Improving LLMs Through Recursive Prob…

200 papers

Deep reinforcement learning (DRL) shows promising potential for autonomous driving decision-making. However, DRL demands extensive computational resources to achieve a qualified policy in complex driving scenarios due to its low learning…

Robotics · Computer Science 2024-12-25 Hao Pang , Zhenpo Wang , Guoqiang Li

Improving Large Language Model (LLM) agents for sequential decision-making tasks typically requires extensive task-specific knowledge engineering--custom prompts, curated examples, and specialized observation/action spaces. We investigate a…

Machine Learning · Computer Science 2025-05-20 Vishnu Sarukkai , Zhiqiang Xie , Kayvon Fatahalian

Autoregressive (AR) Large Language Models (LLMs) have demonstrated significant success across numerous tasks. However, the AR modeling paradigm presents certain limitations; for instance, contemporary autoregressive LLMs are trained to…

Machine Learning · Computer Science 2025-02-10 Justin Deschenaux , Caglar Gulcehre

Large language models (LLMs) have shown impressive capabilities across diverse settings, but still struggle as the length and complexity of the context increases. To address this challenge, we propose Thinking Recursively and Dynamically…

Computation and Language · Computer Science 2025-08-05 Philip Schroeder , Nathaniel Morgan , Hongyin Luo , James Glass

Test-time scaling methods improve the capabilities of large language models (LLMs) by increasing the amount of compute used during inference to make a prediction. Inference-time compute can be scaled in parallel by choosing among multiple…

The tool-using capability of large language models (LLMs) enables them to access up-to-date external information and handle complex tasks. Current approaches to enhancing this capability primarily rely on distilling advanced models by data…

Computation and Language · Computer Science 2025-05-13 Xu Huang , Weiwen Liu , Xingshan Zeng , Yuefeng Huang , Xinlong Hao , Yuxian Wang , Yirong Zeng , Chuhan Wu , Yasheng Wang , Ruiming Tang , Defu Lian

Dense retrieval calls for discriminative embeddings to represent the semantic relationship between query and document. It may benefit from the using of large language models (LLMs), given LLMs' strong capability on semantic understanding.…

Computation and Language · Computer Science 2025-11-25 Zheng Liu , Chaofan Li , Shitao Xiao , Yingxia Shao , Defu Lian

Large Language Models (LLMs) have demonstrated significant success across various domains. However, their application in complex decision-making tasks frequently necessitates intricate prompt engineering or fine-tuning, leading to…

Artificial Intelligence · Computer Science 2024-05-06 Wanpeng Zhang , Zongqing Lu

Large Language Models (LLMs) exhibit remarkable capabilities but are prone to generating inaccurate or hallucinatory responses. This limitation stems from their reliance on vast pretraining datasets, making them susceptible to errors in…

Computation and Language · Computer Science 2024-04-02 Chi-Min Chan , Chunpu Xu , Ruibin Yuan , Hongyin Luo , Wei Xue , Yike Guo , Jie Fu

LLMs have shown strong potential to advance scientific discovery. Whether they possess the capacity for foundational innovation, however, remains an open question. In this work, we focus on a prerequisite for foundational innovation: can…

Artificial Intelligence · Computer Science 2026-04-08 Jian Zhao , Haoren Luo , Yu Wang , Yuhan Cao , Pingyue Sheng , Tianxing He

Ensuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and reinforcement learning with human feedback have shown promise, they require a substantial…

Machine Learning · Computer Science 2026-03-17 Manh Nguyen , Sunil Gupta , Hung Le

With the development of artificial intelligence (AI), large language models (LLM) are widely used in many fields. However, the reasoning ability of LLM is still very limited when it comes to mathematical reasoning. Mathematics plays an…

Computation and Language · Computer Science 2024-08-06 Wenbei Xie , Donglin Liu , Haoran Yan , Wenjie Wu , Zongyang Liu

Reinforcement Learning (RL) has shown promise in improving the reasoning abilities of Large Language Models (LLMs). However, the specific challenges of adapting RL to multimodal data and formats remain relatively unexplored. In this work,…

Machine Learning · Computer Science 2025-05-20 Zirun Guo , Minjie Hong , Tao Jin

In this paper, we show that the performance of a learnt generative model is closely related to the model's ability to accurately represent the inferred \textbf{latent data distribution}, i.e. its topology and structural properties. We…

Computer Vision and Pattern Recognition · Computer Science 2020-09-02 Shuyu Lin , Ronald Clark

Large language models (LLMs) achieve higher accuracy on challenging reasoning tasks by scaling test-time compute through multiple trajectory sampling. However, standard aggregation methods like majority voting or individual confidence-based…

Machine Learning · Computer Science 2026-02-04 Yingchuan Zhang , Terry Ma , Wenxuan Zhong , Ping Ma

Building upon large language models (LLMs), recent large multimodal models (LMMs) unify cross-model understanding and generation into a single framework. However, LMMs still struggle to achieve accurate vision-language alignment, prone to…

Artificial Intelligence · Computer Science 2025-09-09 Jixiang Hong , Yiran Zhang , Guanzhong Wang , Yi Liu , Ji-Rong Wen , Rui Yan

In-context learning, the ability to adapt based on a few examples in the input prompt, is a ubiquitous feature of large language models (LLMs). However, as LLMs' in-context learning abilities continue to improve, understanding this…

Machine Learning · Computer Science 2024-10-03 Can Demircan , Tankred Saanum , Akshay K. Jagadish , Marcel Binz , Eric Schulz

The reasoning abilities of large language models (LLMs) have been substantially improved by reinforcement learning with verifiable rewards (RLVR). At test time, collaborative reasoning through Multi-Agent Debate (MAD) has emerged as a…

Computation and Language · Computer Science 2026-05-19 Chenxi Liu , Yanshuo Chen , Ruibo Chen , Tianyi Xiong , Tong Zheng , Heng Huang

Large Language Models (LLMs) often struggle with problems that require multi-step reasoning. For small-scale open-source models, Reinforcement Learning with Verifiable Rewards (RLVR) fails when correct solutions are rarely sampled even…

Computation and Language · Computer Science 2026-03-02 Yihe Deng , I-Hung Hsu , Jun Yan , Zifeng Wang , Rujun Han , Gufeng Zhang , Yanfei Chen , Wei Wang , Tomas Pfister , Chen-Yu Lee

Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency: reinforcement learning (RL) training requires long rollouts for outcome-based rewards, where autoregressive decoding dominates time and…

Machine Learning · Computer Science 2026-02-20 Zeliang Zhang , Xiaodong Liu , Hao Cheng , Hao Sun , Chenliang Xu , Jianfeng Gao