English
Related papers

Related papers: Self-Taught Optimizer (STOP): Recursively Self-Imp…

200 papers

Popular prompt strategies like Chain-of-Thought Prompting can dramatically improve the reasoning abilities of Large Language Models (LLMs) in various domains. However, such hand-crafted prompt-strategies are often sub-optimal. In this…

Computation and Language · Computer Science 2023-10-02 Chrisantha Fernando , Dylan Banarse , Henryk Michalewski , Simon Osindero , Tim Rocktäschel

Learning to program can be challenging, and providing high-quality and timely support at scale is hard. Generative AI and its products, like ChatGPT, can create a solution for most intro-level programming problems. However, students might…

Computers and Society · Computer Science 2024-05-31 Xinying Hou , Zihan Wu , Xu Wang , Barbara J. Ericson

A promising research direction in enabling LLMs to generate consistently correct code involves addressing their inability to properly estimate program execution, particularly for code they generate. In this work, we demonstrate that Code…

Computation and Language · Computer Science 2026-04-07 Gallil Maimon , Ori Yoran , Felix Kreuk , Michael Hassid , Gal Cohen , Pierre Chambon , Yossi Adi

A less complex and more straightforward program is a crucial factor that enhances its maintainability and makes writing secure and bug-free programs easier. However, due to its heavy workload and the risks of breaking the working programs,…

Programming Languages · Computer Science 2024-04-08 Atsushi Shirafuji , Yusuke Oda , Jun Suzuki , Makoto Morishita , Yutaka Watanobe

Iteratively improving and repairing source code with large language models (LLMs), known as refinement, has emerged as a popular way of generating programs that would be too complex to construct in one shot. Given a bank of test cases,…

Software Engineering · Computer Science 2024-10-31 Hao Tang , Keya Hu , Jin Peng Zhou , Sicheng Zhong , Wei-Long Zheng , Xujie Si , Kevin Ellis

A common and effective means for improving language model capabilities involves finetuning a ``student'' language model's parameters on generations from a more proficient ``teacher'' model. Termed ``synthetic data'', these generations are…

Existing self-evolution methods overlook the influence of fine-grained reasoning steps, which leads to the reasoner-verifier gap. The computational inefficiency of Monte Carlo (MC) process supervision further exacerbates the difficulty in…

Computation and Language · Computer Science 2026-02-03 Kaiyuan Chen , Guangmin Zheng , Jin Wang , Xiaobing Zhou , Xuejie Zhang

Recent advances in large language model (LLM) reasoning through reinforcement learning rely on annotated datasets for verifiable rewards, which may limit models' ability to surpass human-level performance. While self-play offers a promising…

Computation and Language · Computer Science 2026-01-01 Wai-Chung Kwan , Joshua Ong Jun Leang , Pavlos Vougiouklis , Jeff Z. Pan , Marco Valentino , Pasquale Minervini

Small language models (SLMs) are more efficient, cost-effective, and customizable than large language models (LLMs), though they often underperform in specific areas like reasoning. Past methods for enhancing SLMs' reasoning, such as…

Computation and Language · Computer Science 2024-12-12 Kaiyuan Chen , Jin Wang , Xuejie Zhang

Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks, such as chain-of-thought (CoT) reasoning. However, most of the existing approaches to enhance this ability rely…

Computation and Language · Computer Science 2024-08-08 Xinyi Wang , Lucas Caccia , Oleksiy Ostapenko , Xingdi Yuan , William Yang Wang , Alessandro Sordoni

Recent studies operationalize self-improvement through coding agents that edit their own codebases. They grow a tree of self-modifications through expansion strategies that favor higher software engineering benchmark performance, assuming…

Artificial Intelligence · Computer Science 2025-10-30 Wenyi Wang , Piotr Piękos , Li Nanbo , Firas Laakom , Yimeng Chen , Mateusz Ostaszewski , Mingchen Zhuge , Jürgen Schmidhuber

Large language models (LLMs) make remarkable progress in reasoning tasks. Among different reasoning modes, inductive reasoning, due to its better alignment with human learning, attracts increasing interest. However, research on inductive…

Computation and Language · Computer Science 2025-10-17 Kedi Chen , Zhikai Lei , Xu Guo , Xuecheng Wu , Siyuan Zeng , Jianghao Yin , Yinqi Zhang , Qin Chen , Jie Zhou , Liang He , Qipeng Guo , Kai Chen , Wei Zhang

The self-improving ability of large language models (LLMs), enabled by prompting them to analyze and revise their own outputs, has garnered significant interest in recent research. However, this ability has been shown to be absent and…

Computation and Language · Computer Science 2024-04-02 Xiao Yu , Baolin Peng , Michel Galley , Jianfeng Gao , Zhou Yu

We posit that to achieve superhuman agents, future models require superhuman feedback in order to provide an adequate training signal. Current approaches commonly train reward models from human preferences, which may then be bottlenecked by…

Computation and Language · Computer Science 2025-03-31 Weizhe Yuan , Richard Yuanzhe Pang , Kyunghyun Cho , Xian Li , Sainbayar Sukhbaatar , Jing Xu , Jason Weston

In various fields of knowledge creation, including science, new ideas often build on pre-existing information. In this work, we explore this concept within the context of language models. Specifically, we explore the potential of…

Computation and Language · Computer Science 2024-04-04 David Herel , Tomas Mikolov

Recent language models achieve impressive results in tasks involving complex multistep reasoning, but scaling these capabilities further traditionally requires expensive collection of more annotated data. In this work, we explore the…

Computation and Language · Computer Science 2024-10-25 Marek Kadlčík , Michal Štefánik

Self-improvement is a significant techniques within the realm of large language model (LLM), aiming to enhance the LLM performance without relying on external data. Despite its significance, generally how LLM performances evolve during the…

Machine Learning · Computer Science 2026-02-10 Yifan Sun , Yushan Liang , Zhen Zhang , Xin Liu , Jiaye Teng

Large Language Models (LLMs) are nowadays extensively used for various types of software engineering tasks, primarily code generation. Previous research has shown how suitable prompt engineering could help developers in improving their code…

Code generation, the task of creating executable programs from natural language requirements, has recently seen tremendous advances through Chain-of-Thought (CoT) reasoning, which enables Large Language Models (LLMs) to develop high-level…

Software Engineering · Computer Science 2025-10-21 Shuzheng Gao , Chaozheng Wang , Cuiyun Gao , Michael R. Lyu

LLM agents acting in structured environments fail in operational rather than conversational ways, and reliability depends on procedural knowledge of the environment. Prior self-improvement methods accumulate natural-language guidance…

Artificial Intelligence · Computer Science 2026-05-29 Johannes Moll , Jean-Philippe Corbeil , Jiazhen Pan , Martin Hadamitzky , Daniel Rueckert , Lisa Adams , Keno Bressem