相关论文: Seed-CTS: Unleashing the Power of Tree Search for …

Pre-trained on massive amounts of code and text data, large language models (LLMs) have demonstrated remarkable achievements in performing code generation tasks. With additional execution-based feedback, these models can act as agents with…

The growing scale of Large Language Models (LLMs) has exacerbated inference latency and computational costs. Speculative decoding methods, which aim to mitigate these issues, often face inefficiencies in the construction of token trees and…

Code generation has been greatly enhanced by the profound advancements in Large Language Models (LLMs) recently. Nevertheless, such LLM-based code generation approaches still struggle to generate error-free code in a few tries when faced…

Recent research suggests that tree search algorithms (e.g. Monte Carlo Tree Search) can dramatically boost LLM performance on complex mathematical reasoning tasks. However, they often require more than 10 times the computational resources…

Recent studies explored integrating state-space search algorithms with Language Models (LM) to perform look-ahead on the token generation process, the ''Tree-of-Thoughts'' (ToT), generated by LMs, thereby improving performance on…

Solving complex reasoning tasks is a key real-world application of agents. Thanks to the pretraining of Large Language Models (LLMs) on code data, recent approaches like CodeAct successfully use code as LLM agents' action, achieving good…

Tree-search decoding is an effective form of test-time scaling for large language models (LLMs), but real-world deployment imposes a fixed per-query token budget that varies across settings. Existing tree-search policies are largely…

Competitive program generation aims to automatically produce correct and efficient solutions for programming-contest problems under strict time and memory constraints. Existing LLM-based approaches often fail to perform explicit algorithmic…

Recently, test-time scaling has garnered significant attention from the research community, largely due to the substantial advancements of the o1 model released by OpenAI. By allocating more computational resources during the inference…

Large Language Models (LLMs) have exhibited exceptional performance across a broad range of tasks and domains. However, they still encounter difficulties in solving mathematical problems due to the rigorous and logical nature of…

Code generation is one of the tasks for which the use of Large Language Models is widely adopted and highly successful. Given this popularity, there are many benchmarks dedicated to code generation that can help select the best model.…

Search-based procedural content generation uses stochastic global optimization algorithms to search for game content. However, standard tree search algorithms can be competitive with evolution on some optimization problems. We investigate…

We frame code generation as a black-box optimization problem within the code space and demonstrate how optimization-inspired techniques can enhance inference scaling. Based on this perspective, we propose SCATTERED FOREST SEARCH (SFS), a…

Large Language Models (LLMs) have demonstrated remarkable potential in code generation. The integration of Chain of Thought (CoT) reasoning can further boost their performance. However, current CoT methods often require manual writing or…

Modern reasoning models, such as OpenAI's o1 and DeepSeek-R1, exhibit impressive problem-solving capabilities but suffer from critical inefficiencies: high inference latency, excessive computational resource consumption, and a tendency…

Large language models (LLMs) have shown remarkable ability to generate code, yet their outputs often violate syntactic or semantic constraints when guided only through natural language prompts. We introduce TreeCoder, the most general and…

The quality of mesh generation has long been considered a vital aspect in providing engineers with reliable simulation results throughout the history of the Finite Element Method (FEM). The element extraction method, which is currently the…

Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code…

Large language models (LLMs) have demonstrated significant potential in code generation tasks. However, there remains a performance gap between open-source and closed-source models. To address this gap, existing approaches typically…

In this paper, we propose a policy-guided Monte Carlo Tree Search (MCTS) decoder that achieves near maximum-likelihood decoding (MLD) performance for short block codes. The MCTS decoder searches for test error patterns (TEPs) in the…