Ockhamareto is introduced, a single-shot GRPO framework for unit-test generation and selection, based on the principles of Ockham's Razor and Pareto Optimality, and it is shown that the knee point of the optimal trade-off between efficiency and effectiveness on the Pareto front is not correlated with obvious more easil...
Dong Huang, Mark Harman, Jie M. Zhang et al.· 3 citations
This work proposes CodeScaler, a reward model designed to scale both reinforcement learning training and test-time inference for code generation, and surpasses existing reward models on RM-Bench not only in the code domain, but also in general and reasoning domains.
Xiao Zhu, Xinyu Zhou, Boyuan Zhu et al.· 2 citations
Large Language Models (LLMs) have shown strong performance on tool-use agentic tasks when given a fixed tool schema. Yet a tool schema is not the action space of an agent; it is merely one interface representation of it. The same executable action can be exposed through many different, functionally equivalent tool defi...
Yinhong Liu, Zhi-Li Tan, Zi-Lin Wang et al.· 0 citations
Low-Entropy Discrete Flow (LEDFlow), a training-free sampler that adaptively orders absorption by local entropy, is proposed, and it is shown that, under entropy-error regularity, selecting the lowest-entropy positions under a fixed absorption count minimizes an upper bound on the conditional term.
Tung Sum Thomas Kwok, Yi-Dong Ouyang, Yingjia Wan et al.· 0 citations
FormalRx is introduced, a comprehensive diagnostic evaluation framework that transforms autoformalization assessment from black-box judgments into actionable feedback, and enables systematic diagnosis and improvement of autoformalization systems.
Haocheng Wang, Baiyu Huang, Yingjia Wan et al.· arXiv.org· 1 citation
Experiments on LoCoMo and LongMemEval show that MemoryCPT improves the cost-performance trade-off over the evaluated baselines, while ablation and sensitivity analyses characterize the contributions of its components and the effects of key design choices.
Songxin Lei, Kun Ouyang, Wei-Lin Ruan et al.· 1 citation· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
