$\texttt{YC-Bench}$: Benchmarking AI Agents for Long-Term Planning and Consistent Execution

• URL: http://arxiv.org/abs/2604.01212v1
• Date: Wed, 01 Apr 2026 17:52:19 GMT
• Title: $\texttt{YC-Bench}$: Benchmarking AI Agents for Long-Term Planning and Consistent Execution
• Abstract summary: We introduce $texttYC-Bench$, a benchmark that evaluates capabilities by tasking an agent with running a simulated startup over a one-year horizon spanning hundreds of turns.<n>We evaluate 12 models, both proprietary and open source, across 3 seeds each.<n>Only three models consistently surpass the starting capital of $200K, with Claude Opus 4.6 achieving the highest average final funds at $1.27 M, followed by GLM-5 at $1.21 M at 11$times$ lower inference cost.
• Score: 38.30265058791818
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As LLM agents tackle increasingly complex tasks, a critical question is whether they can maintain strategic coherence over long horizons: planning under uncertainty, learning from delayed feedback, and adapting when early mistakes compound. We introduce $\texttt{YC-Bench}$, a benchmark that evaluates these capabilities by tasking an agent with running a simulated startup over a one-year horizon spanning hundreds of turns. The agent must manage employees, select task contracts, and maintain profitability in a partially observable environment where adversarial clients and growing payroll create compounding consequences for poor decisions. We evaluate 12 models, both proprietary and open source, across 3 seeds each. Only three models consistently surpass the starting capital of \$200K, with Claude Opus 4.6 achieving the highest average final funds at \$1.27 M, followed by GLM-5 at \$1.21 M at 11$\times$ lower inference cost. Scratchpad usage, the sole mechanism for persisting information across context truncation, is the strongest predictor of success, and adversarial client detection is the primary failure mode, accounting for $47\%$ of bankruptcies. Our analysis reveals that frontier models still fail through distinct failure modes such as over-parallelization, demonstrating the capability gaps for long-horizon performance. $\texttt{YC-Bench}$ is open-source, reproducible, and configurable.

Related papers

• When Not to Imitate: Boundary-Aware Skill Memory for Reliable Tool-Use LLM Agents [62.10623192614306]
  Extracting skills from past successes is critical for the efficient evolution of Large Language Model (LLM) agents.<n>We propose textbfBoundary-Aware Skill Memory (BASM), which augments each skill with explicit boundary fields.<n>BASM consistently outperforms success-distilled skill-memory baselines.
  arXiv  Detail & Related papers  (2026-08-23T10:16:06Z)
• Deployment Decision Reliability: A Generalizability-Theory Framework for Sizing Long-Horizon Agent Evaluations [0.0]
  We show, across three open agent-trace benchmarks, that the agent main effect accounts for less than 3% of total variance in every dataset and check type.<n>We arrive at this through a four-facet Generalizability Theory variance decomposition, fit with three estimators.<n>We package these into Deployment Decision Reliability (DDR), a one-page reporting discipline that turns the variance-component table into five decisions an enterprise buyer can defend.
  arXiv  Detail & Related papers  (2026-08-11T18:16:51Z)
• Scaling Laws for Agent Harnesses via Effective Feedback Compute [53.68149869349268]
  emphEffective Feedback Compute (EFC) is a trace-level scaling coordinate that credits feedback only when it is informative, valid, non-redundant, and retained for subsequent decisions.<n>EFC-based coordinates consistently predict failure rates better than raw-compute baselines.
  arXiv  Detail & Related papers  (2026-05-28T09:45:47Z)
• A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks [25.713629634281077]
  We propose TASTE: Task Synthesis from Tool Sequence Evolution, an automatic method that generates challenging tasks with broader tool-use coverage.<n> TASTE selects representative sequences from the pool via clustering, instantiates them into complete benchmark tasks, and refines them through difficulty evolution.<n>Our results suggest high scores on existing benchmarks often reflect saturation rather than robust task-solving ability.
  arXiv  Detail & Related papers  (2026-05-27T14:45:59Z)
• 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)
• The Bureaucracy of Speed: Structural Equivalence Between Memory Consistency Models and Multi-Agent Authorization Revocation [0.0]
  We develop a Capability Coherence System for Identity and Access Management.<n>A safety theorem bounds unauthorized operations for the execution-count Release Consistency-directed Coherence strategy.<n> Tick-based discrete event simulation confirms per-capability safety guarantee.
  arXiv  Detail & Related papers  (2026-03-10T16:37:02Z)
• Capable but Unreliable: Canonical Path Deviation as a Causal Mechanism of Agent Failure in Long-Horizon Tasks [0.38991526486631006]
  We argue that many reliability failures are caused by drift from a task's latent solution structure, not capability failures.<n>We establish this causally using a natural experiment that holds model capability and task difficulty fixed by construction.
  arXiv  Detail & Related papers  (2026-02-22T02:37:57Z)
• MagicAgent: Towards Generalized Agent Planning [73.21129030631421]
  We present textbfMagicAgent, a series of foundation models specifically designed for generalized agent planning.<n>We introduce a lightweight and scalable synthetic data framework that generates high-quality trajectories across diverse planning tasks.<n>We show that MagicAgent-32B and MagicAgent-30B-A3B achieve superior performance across diverse open-source benchmarks.
  arXiv  Detail & Related papers  (2026-02-22T01:39:16Z)
• Phase Transition for Budgeted Multi-Agent Synergy [41.486076708302456]
  Multi-agent systems can improve reliability, yet under a fixed inference budget they often help, saturate, or even collapse.<n>We develop a minimal and calibratable theory that predicts these regimes from three binding constraints of modern agent stacks.
  arXiv  Detail & Related papers  (2026-01-24T05:32:50Z)
• ReliabilityBench: Evaluating LLM Agent Reliability Under Production-Like Stress Conditions [0.32928123659012326]
  Existing benchmarks for tool-using LLM agents primarily report single-run success rates and miss reliability properties required in production.<n>We introduce textbfReliabilityBench, a benchmark for evaluating agent reliability across three dimensions.<n>We evaluate two models (Gemini 2.0 Flash, GPT-4o) and two agent architectures (ReAct, Reflexion) across four domains (scheduling, travel, customer support, e-commerce) over 1,280 episodes.
  arXiv  Detail & Related papers  (2026-01-03T13:41:33Z)
• MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use [27.978435634514128]
  MCPMark is a benchmark designed to evaluate MCP use in a more realistic and comprehensive manner.<n>It consists of $127$ high-quality tasks collaboratively created by domain experts and AI agents.<n>On average, LLMs require $16.2$ execution turns and $17.4$ tool calls per task, significantly surpassing those in previous MCP benchmarks.
  arXiv  Detail & Related papers  (2025-09-28T17:53:27Z)
• Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments [54.67512489842682]
  Large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments.<n>We take a first step toward exploring the early-exit behavior for LLM-based agents.
  arXiv  Detail & Related papers  (2025-05-23T08:23:36Z)
• On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents [58.79302663733703]
  Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents.<n>The impact of clumsy or even malicious agents--those who frequently make errors in their tasks--on the overall performance of the system remains underexplored.<n>This paper investigates what is the resilience of various system structures under faulty agents on different downstream tasks.
  arXiv  Detail & Related papers  (2024-08-02T03:25:20Z)

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.