paper-with-me

홈 › Papers

Treefix: Enabling Execution with a Tree of Prefixes

2025-01-21 · Beatriz Souza, Michael Pradel

The ability to execute code is a prerequisite for various dynamic program analyses. Learning-guided execution has been proposed as an approach to enable the execution of arbitrary code snippets by letting a neural model predict likely values for any missing variables. Although state-of-the-art learning-guided execution approaches, such as LExecutor, can enable the execution of a relative high amount of code, they are limited to predicting a restricted set of possible values and do not use any feedback from previous executions to execute even more code. This paper presents Treefix, a novel learning-guided execution approach that leverages LLMs to iteratively create code prefixes that enable the execution of a given code snippet. The approach addresses the problem in a multi-step fashion, where each step uses feedback about the code snippet and its execution to instruct an LLM to improve a previously generated prefix. This process iteratively creates a tree of prefixes, a subset of which is returned to the user as prefixes that maximize the number of executed lines in the code snippet. In our experiments with two datasets of Python code snippets, Treefix achieves 25% and 7% more coverage relative to the current state of the art in learning-guided execution, covering a total of 84% and 82% of all lines in the code snippets.

📄 PDF Abstract BibTeX arXiv:2501.12339

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Stage-based Hyper-parameter Optimization for Deep Learning

2019-11-24 · Ahnjae Shin, Dong-Jin Shin, Sungwoo Cho, Do Yoon Kim 외

As deep learning techniques advance more than ever, hyper-parameter optimization is the new major workload in deep learning clusters. Although hyper-parameter optimization is crucial in training deep learning models for …

Deep LearningGPU

AREAL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language Models

2026-01-31 · Jiarui Zhang, Yuchen Yang, Ran Yan, Zhiyu Mei 외 arxiv

Reinforcement learning (RL)-based post-training for large language models (LLMs) is computationally expensive, as it generates many rollout sequences that frequently share long token prefixes. Existing RL frameworks usua…

Reinforcement Learning

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse

2025-11-01 · Jinghui Wang, Shaojie Wang, Yinghan Cui, Xuxing Chen 외 arxiv

Agentic large language model (LLM) training often involves multi-turn interaction trajectories that branch into multiple execution paths due to concurrent tool use, think-mode, sub-agent, context management and other run…

Reinforcement Learning

PhyGile: Physics-Prefix Guided Motion Generation for Agile General Humanoid Motion Tracking

2026-03-13 · Jiacheng Bao, Haoran Yang, Yucheng Xin, Junhong Liu 외 arxiv

Humanoid robots are expected to execute agile and expressive whole-body motions in real-world settings. Existing text-to-motion generation models are predominantly trained on captured human motion datasets, whose priors …

DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference

2024-03-30 · Jinwei Yao, Kaiqi Chen, Kexun Zhang, Jiaxuan You 외

Large language models (LLMs) are increasingly employed for complex tasks that process multiple generation calls in a tree structure with shared prefixes of tokens, including few-shot prompting, multi-step reasoning, spec…

GPU