提出主动避坑策略，提升长文本推理中计划的可靠性。
PPA-Plan: Proactive Pitfall Avoidance for Reliable Planning in Long-Context LLM Reasoning
- 生成计划前先识别逻辑陷阱，用负面约束约束规划过程。
- 在长文本问答任务上，性能超越现有规划方法和直接提示。
- 适合需要高可靠性的复杂推理场景，如法律、医疗分析。
大型语言模型在长上下文推理中面临信息稀疏分布的挑战。尽管计划-执行框架通过任务分解缓解此问题，但其效果常受限于依赖表面线索的不可靠计划生成。这导致计划基于错误假设，且一旦形成便难以发现错误并可靠修正，限制了事后优化的效果。为此，我们提出PPA-Plan，一种面向长上下文推理的主动规划策略，旨在计划生成前预防失败。该方法识别潜在逻辑陷阱与错误假设，将其形式化为负向约束，并显式约束计划生成以避免这些陷阱。在多个长文本问答基准上的实验表明，由PPA-Plan生成的计划执行效果持续优于现有计划-执行方法及直接提示法。
原文摘要 · Abstract (English)
Large language models (LLMs) struggle with reasoning over long contexts where relevant information is sparsely distributed. Although plan-and-execute frameworks mitigate this by decomposing tasks into planning and execution, their effectiveness is often limited by unreliable plan generation due to dependence on surface-level cues. Consequently, plans may be based on incorrect assumptions, and once a plan is formed, identifying what went wrong and revising it reliably becomes difficult, limiting the effectiveness of reactive refinement. To address this limitation, we propose PPA-Plan, a proactive planning strategy for long-context reasoning that focuses on preventing such failures before plan generation. PPA-Plan identifies potential logical pitfalls and false assumptions, formulates them as negative constraints, and conditions plan generation on explicitly avoiding these constraints. Experiments on long-context QA benchmarks show that executing plans generated by PPA-Plan consistently outperforms existing plan-and-execute methods and direct prompting.
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。