The Fellowship of the Query: Learning Retrieval Actions

arXiv:2609.28653 · cs.IR, cs.AI, cs.CL, cs.LG · Submitted 2026-09-23 · Read on arXiv

cs.IR, cs.AI, cs.CL, cs.LG

Submitted: 2026-09-23

Updated: 2026-09-23

Code: https://github.com/padas-lab-de/agent-action-controller

Terminology

• Accuracy — 8× in this paper · explained in 1 episode
• Fine-Tuning — 8× in this paper · explained in 5 episodes
• RAG — 6× in this paper · explained in 3 episodes
• Trace — 5× in this paper · explained in 2 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes

Sources

• MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
• LFM2 Technical Report
• Lessons from the Trenches on Reproducible Evaluation of Language Models
• RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation
• Ministral 3
• Augmented Language Models: a Survey
• MiniCPM4: Ultra-Efficient LLMs on End Devices
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Qwen3 Technical Report
• MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Related papers

• The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
• SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
• MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
• RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
• Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
• UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG