Research Papers 论文研究 4h ago Updated 1h ago 更新于 1小时前 49

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading 长期视界终端基准:使用密集奖励评分测试智能体在长期视界终端任务中的极限

Introduction of Long-Horizon-Terminal-Bench, a new evaluation suite featuring 46 complex, multi-step terminal tasks designed to test long-horizon agent capabilities. Implementation of a dense reward-based grading system that decomposes tasks into fine-grained subtasks, enabling partial credit and capturing intermediate progress rather than just binary success. Empirical evaluation of 15 frontier models reveals extremely low performance, with top-tier models achieving only 15.2% pass rate at a 0. 提出 Long-Horizon-Terminal-Bench,包含46个长周期终端任务,覆盖软件工程、科学计算等九类领域。 引入基于密集奖励的细粒度子任务分解机制,解决传统基准测试中奖励稀疏、无法评估中间进度的问题。 评估15个前沿模型,平均每个任务消耗990万Token,执行时间约85分钟,当前最强模型完美通过率仅10.9%。 揭示了现有AI代理在长期规划、上下文管理及迭代调试方面的显著能力瓶颈与改进空间。

65
Hot 热度
75
Quality 质量
70
Impact 影响力

Analysis 深度分析

TL;DR

  • Introduction of Long-Horizon-Terminal-Bench, a new evaluation suite featuring 46 complex, multi-step terminal tasks designed to test long-horizon agent capabilities.
  • Implementation of a dense reward-based grading system that decomposes tasks into fine-grained subtasks, enabling partial credit and capturing intermediate progress rather than just binary success.
  • Empirical evaluation of 15 frontier models reveals extremely low performance, with top-tier models achieving only 15.2% pass rate at a 0.95 partial-reward threshold and 10.9% at perfect completion.
  • The benchmark highlights significant resource intensity, with agents averaging 9.9M tokens, 231 episodes, and over 85 minutes of execution time per task, stressing planning and context management.

Why It Matters

This benchmark addresses a critical gap in AI evaluation by moving beyond simple, short-term tasks to assess agents' ability to handle complex, open-ended workflows that mimic real-world software engineering and scientific computing scenarios. For researchers and practitioners, it provides a rigorous standard for measuring long-horizon planning, iterative debugging, and context retention, exposing the substantial limitations of current state-of-the-art models in sustained autonomous operation.

Technical Details

  • Benchmark Structure: Consists of 46 tasks across nine categories (e.g., experiment reproduction, software engineering, scientific computing), each requiring hundreds of interaction episodes and lasting from minutes to hours.
  • Evaluation Methodology: Utilizes a dense reward signal derived from fine-grained subtask decomposition, allowing for partial credit assessment based on intermediate progress rather than a binary final outcome.
  • Resource Consumption Metrics: Average token consumption is 9.9M per task, with approximately 231 episodes and 85.3 minutes of execution time, significantly exceeding prior terminal benchmarks.
  • Performance Baselines: Evaluated on 15 frontier models; the best-performing model achieved 15.2% pass@1 at a 0.95 reward threshold, while the mean pass rate across all models was only 4.3%, indicating vast room for improvement in long-horizon reasoning.

Industry Insight

  • Shift in Evaluation Standards: The industry must transition from evaluating one-shot problem-solving to assessing sustained, multi-step autonomy, as current metrics fail to capture the nuances of long-horizon agent behavior.
  • Focus on Context Management: The high token usage and episode counts suggest that future model development should prioritize efficient long-context handling and memory management techniques to reduce computational overhead and improve reliability.
  • Iterative Debugging as a Core Capability: Success in these benchmarks relies heavily on iterative debugging and planning; therefore, training methodologies should emphasize self-correction mechanisms and robust error recovery strategies over initial prompt accuracy.

TL;DR

  • 提出 Long-Horizon-Terminal-Bench,包含46个长周期终端任务,覆盖软件工程、科学计算等九类领域。
  • 引入基于密集奖励的细粒度子任务分解机制,解决传统基准测试中奖励稀疏、无法评估中间进度的问题。
  • 评估15个前沿模型,平均每个任务消耗990万Token,执行时间约85分钟,当前最强模型完美通过率仅10.9%。
  • 揭示了现有AI代理在长期规划、上下文管理及迭代调试方面的显著能力瓶颈与改进空间。

为什么值得看

该研究突破了传统终端基准测试仅关注最终结果的局限,通过引入密集奖励机制更真实地反映了AI代理在复杂、长周期工作流中的实际能力。对于致力于开发自主智能体(Autonomous Agents)的研究者和工程师而言,这提供了关键的评估标准和失败模式分析,指明了提升长期任务执行能力的方向。

技术解析

  • 基准设计:构建包含46个长周期任务的终端基准测试,每个任务均分解为细粒度的可评分子任务,支持部分得分(partial credit),从而提供密集的中间奖励信号。
  • 任务复杂度:任务类型涵盖实验复现、软件开发、多模态分析等,要求代理具备数百次交互回合(episodes)的能力,强调长期规划而非一次性解题。
  • 性能数据:在15个前沿模型上的测试显示,单任务平均Token消耗达9.9M,执行时长85.3分钟;在0.95奖励阈值下最高通过率15.2%,完美完成率仅10.9%。
  • 分析维度:除了整体通过率,还深入分析了模型的失败模式和错误分布,为后续优化提供具体依据。

行业启示

  • 评估体系升级:行业应从“结果导向”转向“过程与结果并重”,建立支持细粒度反馈和中间状态评估的新型基准测试标准。
  • 长程能力瓶颈:当前主流模型在处理需长时间上下文管理和反复调试的复杂任务时表现不佳,未来研发需重点加强长期记忆管理和错误恢复机制。
  • 资源消耗警示:长周期Agent任务伴随极高的Token和计算成本,在实际部署前需充分评估经济可行性与效率优化策略。

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Agent Agent Benchmark 基准测试 Evaluation 评测 Research 科学研究