Researchers have developed a new agentic behavior called "Plan" for large language models that decomposes complex questions into ordered sub-questions before retrieval begins. This structured approach aims to improve multi-hop question-answering by anchoring each search step to a pre-designed sub-question, preventing drift from partially relevant documents. The study found that training success depends on model-specific conditions like initial entropy and stability, not just reward design. To address this, a self-bootstrapping paradigm was proposed where a seed model generates filtered trajectories to activate "Plan" in target models, eliminating the need for distillation and consistently outperforming baselines. AI
RANK_REASON This is a research paper detailing a new method for improving LLM agents. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
