English

Atomic Information Flow: A Network Flow Model for Tool Attributions in RAG Systems

Information Retrieval 2026-02-06 v1 Computation and Language Machine Learning

Abstract

Many tool-based Retrieval Augmented Generation (RAG) systems lack precise mechanisms for tracing final responses back to specific tool components -- a critical gap as systems scale to complex multi-agent architectures. We present \textbf{Atomic Information Flow (AIF)}, a graph-based network flow model that decomposes tool outputs and LLM calls into atoms: indivisible, self-contained units of information. By modeling LLM orchestration as a directed flow of atoms from tool and LLM nodes to a response super-sink, AIF enables granular attribution metrics for AI explainability. Motivated by the max-flow min-cut theorem in network flow theory, we train a lightweight Gemma3 (4B parameter) language model as a context compressor to approximate the minimum cut of tool atoms using flow signals computed offline by AIF. We note that the base Gemma3-4B model struggles to identify critical information with \textbf{54.7\%} accuracy on HotpotQA, barely outperforming lexical baselines (BM25). However, post-training on AIF signals boosts accuracy to \textbf{82.71\%} (+28.01 points) while achieving \textbf{87.52\%} (+1.85\%) context token compression -- bridging the gap with the Gemma3-27B variant, a model nearly 7×7\times larger.

Cite

@article{arxiv.2602.04912,
  title  = {Atomic Information Flow: A Network Flow Model for Tool Attributions in RAG Systems},
  author = {James Gao and Josh Zhou and Qi Sun and Ryan Huang and Steven Yoo},
  journal= {arXiv preprint arXiv:2602.04912},
  year   = {2026}
}
R2 v1 2026-07-01T09:36:34.659Z