EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering
Agentic Test-Time Scaling (TTS) has delivered state-of-the-art (SOTA) performance on complex software engineering tasks such as code generation and bug fixing. However, its practical adoption remains limited due to significant computational overhead, primarily driven by two key challenges: (1) the high cost associated with deploying excessively large ensembles, and (2) the lack of a reliable mechanism for selecting the optimal candidate solution, ultimately constraining the performance gains that can be realized. To address these challenges, we propose Entropy-Guided Stepwise Scaling (EGSS), a novel TTS framework that dynamically balances efficiency and effectiveness through entropy-guided adaptive search and robust test-suite augmentation. Extensive experiments on SWE-Bench-Verified demonstrate that EGSS consistently boosts performance by 5-10% across all evaluated models. Specifically, it increases the resolved ratio of Kimi-K2-Intruct from 63.2% to 72.2%, and GLM-4.6 from 65.8% to 74.6%. Furthermore, when paired with GLM-4.6, EGSS achieves a new state-of-the-art among open-source large language models. In addition to these accuracy improvements, EGSS reduces inference-time token usage by over 28% compared to existing TTS methods, achieving simultaneous gains in both effectiveness and computational efficiency.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencyCode GenerationSimilar Papers 제목 키워드 기반
Modeling False Data Injection Attacks in Integrated Electricity-Gas Systems
This work studies the modeling of false data injection attacks (FDIAs) in integrated electricity-gas systems (IEGSs). First, we introduce a static state estimation model and bad data detection method for IEGSs. Then, we …
State EstimationEntropy-Guided Data-Efficient Training for Multimodal Reasoning Reward Models
Multimodal reward models are crucial for aligning multimodal large language models with human preferences. Recent works have incorporated reasoning capabilities into these models, achieving promising results. However, tr…
Multimodal ReasoningCybersecurity and Sustainable Development
Growing interdependencies between organizations lead them towards the creation of inter-organizational networks where cybersecurity and sustainable development have become one of the most important issues. The Environmen…
ManagementQLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search
Language agents have become a promising solution to complex interactive tasks. One of the key ingredients to the success of language agents is the reward model on the trajectory of the agentic workflow, which provides va…
Reinforcement Learning for Diffusion LLMs with Entropy-Guided Step Selection and Stepwise Advantages
Reinforcement learning (RL) has been effective for post-training autoregressive (AR) language models, but extending these methods to diffusion language models (DLMs) is challenging due to intractable sequence-level likel…
Reinforcement LearningMathematical ReasoningLogical Reasoning