Only Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAG

arXiv:2606.22681 · cs.CL, cs.AI · Submitted 2026-06-21 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-06-21

Updated: 2026-09-27

Terminology

• RAG — 155× in this paper · explained in 3 episodes
• Accuracy — 54× in this paper · explained in 1 episode
• Ablation — 17× in this paper · explained in 1 episode
• Pruning — 13× in this paper · explained in 4 episodes
• Verification — 9× in this paper · explained in 2 episodes
• Grounding — 7× in this paper · explained in 3 episodes
• Retrieval-Augmented Generation — 6× in this paper
• Adaptability — 5× in this paper · explained in 1 episode
• Alignment — 5× in this paper · explained in 1 episode
• Robustness — 5× in this paper · explained in 5 episodes
• Ablation study — 3× in this paper · explained in 1 episode
• Hallucination — 3× in this paper · explained in 3 episodes
• Knowledge Graph — 3× in this paper · explained in 7 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Agentic Search — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Exact Match — 2× in this paper
• F1 Score — 2× in this paper · explained in 3 episodes
• Knowledge graphs — 2× in this paper · explained in 2 episodes
• Multi-hop Reasoning — 2× in this paper · explained in 3 episodes
• Retrieval-Augmented Generation (RAG) — 2× in this paper · explained in 16 episodes
• Substring Match — 2× in this paper
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Modular Architecture — 1× in this paper · explained in 4 episodes
• National Science and Technology Council — 1× in this paper
• Query Complexity — 1× in this paper · explained in 2 episodes
• Structured Prompting — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• From Local to Global: A Graph RAG Approach to Query-Focused Summarization
• Retrieval-Augmented Generation for Large Language Models: A Survey
• FrugalRAG: Less is More in RL Finetuning for Multi-Hop Question Answering
• RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning
• A Preliminary Study of RAG for Taiwanese Historical Archives
• MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning
• MultiCube-RAG for Multi-hop Question Answering
• Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
• Plan*RAG: Efficient Test-Time Planning for Retrieval Augmented Generation
• Efficient Agents: Building Effective Agents While Reducing Cost
• RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation
• ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering
• ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
• Corrective Retrieval Augmented Generation
• Credible Plan-Driven RAG Method for Multi-Hop Question Answering

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering