Can LLM Agents Be CFOs? A Benchmark for Resource Allocation in Dynamic Enterprise Environments

• URL: http://arxiv.org/abs/2603.23638v1
• Date: Tue, 24 Mar 2026 18:25:00 GMT
• Title: Can LLM Agents Be CFOs? A Benchmark for Resource Allocation in Dynamic Enterprise Environments
• Abstract summary: We introduce EnterpriseArena, the first benchmark for evaluating agents on long-horizon enterprise resource allocation.<n>It instantiates CFO-style decision-making in a 132-month enterprise simulator combining firm-level financial data, anonymized business documents, macroeconomic and industry signals, and expert-validated operating rules.<n>Experiments show that only 16% of runs survive the full horizon, and larger models do not reliably outperform smaller ones.
• Score: 39.051947374027435
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have enabled agentic systems that can reason, plan, and act across complex tasks, but it remains unclear whether they can allocate resources effectively under uncertainty. Unlike short-horizon reactive decisions, allocation requires committing scarce resources over time while balancing competing objectives and preserving flexibility for future needs. We introduce EnterpriseArena, the first benchmark for evaluating agents on long-horizon enterprise resource allocation. It instantiates CFO-style decision-making in a 132-month enterprise simulator combining firm-level financial data, anonymized business documents, macroeconomic and industry signals, and expert-validated operating rules. The environment is partially observable and reveals the state only through budgeted organizational tools, forcing agents to trade off information acquisition against conserving scarce resources. Experiments on eleven advanced LLMs show that this setting remains highly challenging: only 16% of runs survive the full horizon, and larger models do not reliably outperform smaller ones. These results identify long-horizon resource allocation under uncertainty as a distinct capability gap for current LLM agents.

Related papers

• Can LLMs Be CEOs? Benchmarking Strategic Resource Reallocation with Multi-Role Agent Simulation [5.488097487012986]
  evaluating the decision-making capabilities of large language models (LLMs) is a growing research priority.<n>We introduce textscCEO-Bench, a benchmark that evaluates LLMs on CEO-level strategic resource reallocation.<n> Experiments across five frontier models on 13 scenarios reveal that all models achieve high structural validity but diverge sharply on strategic calibration.
  arXiv  Detail & Related papers  (2026-06-16T03:20:04Z)
• ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox [61.862814740220806]
  $textbfComplexMCP$ is a benchmark designed to evaluate agents in rigorous conditions.<n>Built on the Model Context Protocol (MCP), $textbfComplexMCP$ provides over 300 meticulously tested tools.
  arXiv  Detail & Related papers  (2026-05-11T16:20:51Z)
• Market-Bench: Benchmarking Large Language Models on Economic and Trade Competition [102.73682784993169]
  This paper introduces textbfMarket-Bench, a benchmark that evaluates the capabilities of large language models (LLMs) in economically-relevant tasks.<n>We construct a multi-agent supply chain economic model where LLMs act as retailer agents responsible for procuring and retailing merchandise.<n>Market-Bench logs complete trajectories of bids, prices, slogans, sales, and balance-sheet states, enabling automatic evaluation with economic, operational, and semantic metrics.
  arXiv  Detail & Related papers  (2026-04-07T07:23:51Z)
• CN-Buzz2Portfolio: A Chinese-Market Dataset and Benchmark for LLM-Based Macro and Sector Asset Allocation from Daily Trending Financial News [21.498084305999992]
  Large Language Models (LLMs) are rapidly transitioning from static Natural Language Processing (NLP) tasks to acting as dynamic decision-making agents.<n>Direct live trading is irreproducible and prone to outcome bias by confounding luck with skill, whereas existing static benchmarks are often confined to entity-level stock picking and ignore broader market attention.<n>This work provides new insights into the alignment between general reasoning and financial decision-making, and all data, codes, and experiments are released to promote sustainable financial agent research.
  arXiv  Detail & Related papers  (2026-03-18T02:31:28Z)
• Are Your Agents Upward Deceivers? [73.1073084327614]
  Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users.<n>This raises the question of whether they may also engage in deception, similar to how individuals in human organizations lie to superiors to create a good image or avoid punishment.<n>We observe and define agentic upward deception, a phenomenon in which an agent facing environmental constraints conceals its failure and performs actions that were not requested without reporting.
  arXiv  Detail & Related papers  (2025-12-04T14:47:05Z)
• StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets? [44.10622904101254]
  Large language models (LLMs) have recently demonstrated strong capabilities as autonomous agents.<n>We introduce StockBench, a benchmark designed to evaluate LLM agents in realistic, multi-month stock trading environments.<n>Our evaluation shows that while most LLM agents struggle to outperform the simple buy-and-hold baseline, several models demonstrate the potential to deliver higher returns and manage risk more effectively.
  arXiv  Detail & Related papers  (2025-10-02T16:54:57Z)
• COALESCE: Economic and Security Dynamics of Skill-Based Task Outsourcing Among Team of Autonomous LLM Agents [0.0]
  COALESCE is a novel framework designed to enable autonomous Large Language Model (LLM) agents to outsource specific subtasks to specialized, cost-effective third-party LLM agents.<n> Comprehensive validation through 239 theoretical simulations demonstrates 41.8% cost reduction potential.<n>Large-scale empirical validation across 240 real LLM tasks confirms 20.3% cost reduction with proper epsilon-greedy exploration.
  arXiv  Detail & Related papers  (2025-06-02T17:22:47Z)
• The Real Barrier to LLM Agent Usability is Agentic ROI [110.31127571114635]
  Large Language Model (LLM) agents represent a promising shift in human-AI interaction.<n>We highlight a critical usability gap in high-demand, mass-market applications.
  arXiv  Detail & Related papers  (2025-05-23T11:40:58Z)
• Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents [101.17919953243107]
  GovSim is a generative simulation platform designed to study strategic interactions and cooperative decision-making in large language models (LLMs)<n>We find that all but the most powerful LLM agents fail to achieve a sustainable equilibrium in GovSim, with the highest survival rate below 54%.<n>We show that agents that leverage "Universalization"-based reasoning, a theory of moral thinking, are able to achieve significantly better sustainability.
  arXiv  Detail & Related papers  (2024-04-25T15:59:16Z)
• FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design [11.913409501633616]
  textscFinMem is a novel LLM-based agent framework devised for financial decision-making. textscFinMem's memory module aligns closely with the cognitive structure of human traders, offering robust interpretability. This framework enables the agent to self-evolve its professional knowledge, react agilely to new investment cues, and continuously refine trading decisions.
  arXiv  Detail & Related papers  (2023-11-23T00:24:40Z)
• AgentBench: Evaluating LLMs as Agents [99.12825098528212]
  Large Language Model (LLM) as agents has been widely acknowledged recently.<n>We present AgentBench, a benchmark that consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities.
  arXiv  Detail & Related papers  (2023-08-07T16:08:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.