TAPE让语言模型在复杂任务中更可靠，减少错误导致的失败。
TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agents
- 用工具引导的动态规划图和外部求解器找可行路径
- 执行时约束采样并根据反馈自适应重规划，成功率提升21个百分点
- 特别适合对可靠性要求高的硬任务，如复杂推理和环境交互
语言模型代理在需要多步交互的任务中表现卓越，但在单次错误即导致不可逆失败、且有严格可行性约束的环境中仍易出错。我们系统分析现有框架，发现不完善规划和随机执行是主因。为此提出工具引导的自适应规划与约束执行（TAPE）。TAPE通过聚合多条计划构建图结构，并利用外部求解器寻找可行路径；执行时采用约束解码降低采样噪声，并在环境反馈偏离预期时自适应重规划。在Sokoban、ALFWorld、MuSiQue和GSM8K-Hard上的实验表明，TAPE持续优于现有框架，在困难设置下平均成功率提升21.0个百分点，弱基模型上平均提升20.0个百分点。代码与数据已公开。
原文摘要 · Abstract (English)
Language Model (LM) agents have demonstrated remarkable capabilities in solving tasks that require multiple interactions with the environment. However, they remain vulnerable in environments where a single error often leads to irrecoverable failure, particularly under strict feasibility constraints. We systematically analyze existing agent frameworks, identifying imperfect planning and stochastic execution as the primary causes. To address these challenges, we propose Tool-guided Adaptive Planning with constrained Execution (TAPE). TAPE enhances planning capability by aggregating multiple plans into a graph and employing an external solver to identify a feasible path. During execution, TAPE employs constrained decoding to reduce sampling noise, while adaptively re-planning whenever environmental feedback deviates from the intended state. Experiments across Sokoban, ALFWorld, MuSiQue, and GSM8K-Hard demonstrate that TAPE consistently outperforms existing frameworks, with particularly large gains on hard settings, improving success rates by 21.0 percentage points on hard settings on average, and by 20.0 percentage points for weaker base models on average. Code and data available at here.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。