paper-with-me

Papers

RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning

2024-10-02 · Jonas Gehring, Kunhao Zheng, Jade Copet, Vegard Mella, Taco Cohen, Gabriel Synnaeve

Large language models (LLMs) deployed as agents solve user-specified tasks over multiple steps while keeping the required manual engagement to a minimum. Crucially, such LLMs need to ground their generations in any feedback obtained to reliably achieve desired outcomes. We propose an end-to-end reinforcement learning method for teaching models to leverage execution feedback in the realm of code synthesis, where state-of-the-art LLMs struggle to improve code iteratively compared to independent sampling. We benchmark on competitive programming tasks, where we achieve new start-of-the art results with both small (8B parameters) and large (70B) models while reducing the amount of samples required by an order of magnitude. Our analysis of inference-time behavior demonstrates that our method produces LLMs that effectively leverage automatic feedback over multiple steps.

📄 PDF Abstract BibTeX arXiv:2410.02089

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

HyCodePolicy: Hybrid Language Controllers for Multimodal Monitoring and Decision in Embodied Agents

2025-08-04 · Yibin Liu, Zhixuan Liang, Zanxin Chen, Tianxing Chen 외 arxiv

Recent advances in multimodal large language models (MLLMs) have enabled richer perceptual grounding for code policy generation in embodied agents. However, most existing systems lack effective mechanisms to adaptively m…

Multimodal ReasoningRobot ManipulationProgram Synthesis

MRT at IberLEF-2025 PRESTA Task: Maximizing Recovery from Tables with Multiple Steps

2025-07-17 · Maximiliano Hormazábal Lagos, Álvaro Bueno Sáez, Héctor Cerezo-Costas, Pedro Alonso Doval 외 arxiv

This paper presents our approach for the IberLEF 2025 Task PRESTA: Preguntas y Respuestas sobre Tablas en Español (Questions and Answers about Tables in Spanish). Our solution obtains answers to the questions by implemen…

Code Generation

Octopus: Embodied Vision-Language Programmer from Environmental Feedback

2023-10-12 · Jingkang Yang, Yuhao Dong, Shuai Liu, Bo Li 외

Large vision-language models (VLMs) have achieved substantial progress in multimodal perception and reasoning. When integrated into an embodied agent, existing embodied VLM works either output detailed action sequences a…

BenchmarkingCode GenerationDecision MakingMinecraft

Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents

2026-02-02 · Pengfei He, Ash Fox, Lesly Miculicich, Stefan Friedli 외 arxiv

Large language models (LLMs) have shown promise in assisting cybersecurity tasks, yet existing approaches struggle with automatic vulnerability discovery and exploitation due to limited interaction, weak execution ground…

Vulnerability Detection

Towards Execution-Grounded Automated AI Research

2026-01-20 · Chenglei Si, Zitong Yang, Yejin Choi, Emmanuel Candès 외 arxiv

Automated AI research holds great potential to accelerate scientific discovery. However, current LLMs often generate plausible-looking but ineffective ideas. Execution grounding may help, but it is unclear whether automa…

Reinforcement Learning