Saved in:
Bibliographic Details
Main Authors: Zhou, Lingfeng, Shi, Junhao, Gao, Jin, Wang, Dequan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.10182
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917400469831680
author Zhou, Lingfeng
Shi, Junhao
Gao, Jin
Wang, Dequan
author_facet Zhou, Lingfeng
Shi, Junhao
Gao, Jin
Wang, Dequan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10182
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Credit-Budgeted ICPC-Style Coding: When Agents Must Pay for Every Decision
Zhou, Lingfeng
Shi, Junhao
Gao, Jin
Wang, Dequan
Artificial Intelligence
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.
title Credit-Budgeted ICPC-Style Coding: When Agents Must Pay for Every Decision
topic Artificial Intelligence
url https://arxiv.org/abs/2604.10182