Paper Detail

CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning

Cheng-Yen Li, Xuanjun Chen, Claire Lin, Wei-Yu Chen, Wenhua Nie, Hung-Yi Lee, Jyh-Shing Roger Jang

arxiv Score 18.3

Published 2026-04-12 · First seen 2026-04-14

Research Track A · General AI

Abstract

Large Language Models (LLMs) struggle with knowledge-intensive tasks due to hallucinations and fragmented reasoning over dispersed information. While Retrieval-Augmented Generation (RAG) grounds generation in external sources, existing methods often treat evidence as isolated units, failing to reconstruct the logical chains that connect these dots. Inspired by Complementary Learning Systems (CLS), we propose CodaRAG, a framework that evolves retrieval from passive lookup into active associative discovery. CodaRAG operates via a three-stage pipeline: (1) Knowledge Consolidation to unify fragmented extractions into a stable memory substrate; (2) Associative Navigation to traverse the graph via multi-dimensional pathways-semantic, contextualized, and functional-explicitly recovering dispersed evidence chains; and (3) Interference Elimination to prune hyper-associative noise, ensuring a coherent, high-precision reasoning context. On GraphRAG-Bench, CodaRAG achieves absolute gains of 7-10% in retrieval recall and 3-11% in generation accuracy. These results demonstrate CodaRAG's superior ability to systematically robustify associative evidence retrieval for factual, reasoning, and creative tasks.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{li2026codarag,
  title = {CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning},
  author = {Cheng-Yen Li and Xuanjun Chen and Claire Lin and Wei-Yu Chen and Wenhua Nie and Hung-Yi Lee and Jyh-Shing Roger Jang},
  year = {2026},
  abstract = {Large Language Models (LLMs) struggle with knowledge-intensive tasks due to hallucinations and fragmented reasoning over dispersed information. While Retrieval-Augmented Generation (RAG) grounds generation in external sources, existing methods often treat evidence as isolated units, failing to reconstruct the logical chains that connect these dots. Inspired by Complementary Learning Systems (CLS), we propose CodaRAG, a framework that evolves retrieval from passive lookup into active associative },
  url = {https://arxiv.org/abs/2604.10426},
  keywords = {cs.CL, cs.AI},
  eprint = {2604.10426},
  archiveprefix = {arXiv},
}

Metadata

{}