Year: 2025
Type: conference-paper
Abstract: This position paper proposes a fundamental shift in designing code generation models: treating reasoning depth as a controllable resource. Rather than being an incidental by-product of prompting, we argue that the trade-off between rapid, direct answers ("fast thinking") and elaborate, chain-of-thought deliberation ("slow thinking") must be explicitly managed. We contend that optimizing reasoning budgets across the entire model lifecycle—from synthetic data creation and benchmarking to real-world deployment—can unlock superior trade-offs among accuracy, latency, and cost. This paper outlines how adaptive control over reasoning can enrich supervision signals, motivate new multi-dimensional benchmarks, and inform cost-aware, security-conscious deployment policies. By viewing fast and slow thinking as complementary modes to be scheduled, we envision coding agents that think deep when necessary and act fast when possible.
Authors: Zongjie Li, Shuai Wang
Institution: Hong Kong University of Science and Technology
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4415002697