LLM长时程状态跟踪：通过深度依赖工具调用执行MD5
原标题：Long-Horizon State Tracking in LLMs: Executing MD5 through a Deep Sequence of Dependent Tool Calls
AI 摘要
该研究提出一种受控基准测试，让LLM通过逐步调用工具执行MD5哈希计算，以评估其长时程状态跟踪能力。实验表明，gpt-oss-120b模型在多数运行中能正确完成全部步骤，且当用另一个LLM替代所有原始工具时，驱动-工作模型对也能从零计算哈希。成功的关键在于将模型自身推理保留在上下文中，并对工作模型采用多数投票机制。
正文节选
Long-Horizon State Tracking in LLMs: Executing MD5 through a Deep Sequence of Dependent Tool Calls Abstract Long-horizon tasks remain uncommon in large language model (LLM) evaluation, and for a reason: when each step depends on the last, per-step accuracy that looks excellent in isolation decays catastrophically, as errors cascade and the end-to-end failure probability grows sharply with length. Existing agentic benchmarks report end-to-end success but confound this state-tracking difficulty wi