PPA-Plan: Proactive Pitfall Avoidance for Reliable Planning in Long-Context LLM Reasoning
For LLMs struggling with long-context reasoning, PPA-Plan offers a proactive strategy to enhance plan reliability, though it is an incremental improvement over existing plan-and-execute frameworks.
PPA-Plan improves long-context LLM reasoning by proactively identifying and avoiding logical pitfalls before plan generation, outperforming existing plan-and-execute methods and direct prompting on QA benchmarks.
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.