Credit-Budgeted ICPC-Style Coding: When Agents Must Pay for Every Decision

arXiv:2604.10182v1 Announce Type: new Abstract: Current evaluations of autonomous coding agents assume an unrealistic, infinite-resource environment. However, real-world software engineering is a resource-bound competition. As we scale toward large agent swarms, ignoring compute and time costs risks catastrophic budget exhaustion. To shift the focus from isolated accuracy to cost-aware problem-solving, we introduce USACOArena, an interactive ACM-ICPC-style arena driven by a strict "credit" economy. Every generated token, local test, and elapsed second depletes a fixed budget, forcing agents to make strategic trade-offs. Our comprehensive profiling reveals that frontier single agents and swarms currently fail to optimally balance accuracy with these constraints, exhibiting divergent, path-dependent behaviors. Ultimately, USACOArena provides an essential dynamic training ground for developing highly efficient, resource-aware agent architectures.

Related

• SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context
• SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
• From Helpful to Trustworthy: LLM Agents for Pair Programming
• FM-Agent: Scaling Formal Methods to Large Systems via LLM-Based Hoare-Style Reasoning

Source: arXiv cs.AI | 2026-04-14