mlsanityData to 7 Oct 2026

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

arXiv 2604.10182 ↗First posted 11 Apr 2026cs.AIcited by 2

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 33 of its 41 references that are in the map. First posted on arXiv 11 Apr 2026.

Builds on

33 of 41 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Doc2Feat-Bench: Evaluating Documentation-Driven Feature Addition24 Jul
  2. 2025SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents26 May
  3. 2025DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal18 Mar
  4. 2025ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation10 Mar
  5. 2024Agentless: Demystifying LLM-based Software Engineering Agents1 Jul
  6. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering6 May

Other references · 27

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  2. 2021Program Synthesis with Large Language Modelscited by 3,509
  3. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  4. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  5. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  6. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  7. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 580
  8. 2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 527
  9. 2024TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Taskscited by 306
  10. 2023Magicoder: Empowering Code Generation with OSS-Instructcited by 251
  11. 2024SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?cited by 196
  12. 2024RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learningcited by 146
15 more
  1. 2024AgentScope: A Flexible yet Robust Multi-Agent Platformcited by 120
  2. 2025CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratingscited by 109
  3. 2025SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Taskscited by 108
  4. 2024Can Language Models Solve Olympiad Programming?cited by 70
  5. 2024Evaluating Language Models for Efficient Code Generationcited by 69
  6. 2024Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Explorationcited by 58
  7. 2025LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?cited by 52
  8. 2025Co-Evolving LLM Coder and Unit Tester via Reinforcement Learningcited by 51
  9. 2024RLCoder: Reinforcement Learning for Repository-Level Code Completioncited by 44
  10. 2024Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Studycited by 40
  11. 2024LeDex: Training LLMs to Better Self-Debug and Explain Codecited by 39
  12. 2024Meta Large Language Model Compiler: Foundation Models of Compiler Optimizationcited by 39
  13. 2025Teaching Language Models to Critique via Reinforcement Learningcited by 38
  14. 2025Multi-Turn Code Generation Through Single-Step Rewardscited by 27
  15. 2025ProBench: Benchmarking Large Language Models in Competitive Programmingcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Autonomous Research Agents: A Survey of AI Scientists and the Verification Gapcited by 6
  2. 2026RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026openJiuwen: Beyond Static Harnesses for Long-Horizon Coding Agents
  2. 2026Understanding the Architecture of Coding Agents: An Exploratory Study Using a Research Prototype
  3. 2026OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime
  4. 2026Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures
  5. 2026ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development
  6. 2025AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities
  7. 2026EvoCode-Bench: Evaluating Coding Agents in Multi-Turn Iterative Interactions
  8. 2026CodeMidas: Scaling Agentic Coding RL Environments from Code Itself