Odin: Multi-Signal Graph Intelligence for Autonomous Discovery in Knowledge Graphs

Muyukani Kizito; Elizabeth Nyambere

cs.AIMar 3, 2026

Odin: Multi-Signal Graph Intelligence for Autonomous Discovery in Knowledge Graphs

Authors: Muyukani Kizito, Elizabeth Nyambere

Organizations: Prescott Data

Abstract

We present Odin, the first production-deployed graph intelligence engine for autonomous discovery of meaningful patterns in knowledge graphs without prior specification. Unlike retrieval-based systems that answer predefined queries, Odin guides exploration through the COMPASS (Composite Oriented Multi-signal Path Assessment) score, a novel metric that combines (1) structural importance via Personalized PageRank, (2) semantic plausibility through Neural Probabilistic Logic Learning (NPLL) used as a discriminative filter rather than generative model, (3) temporal relevance with configurable decay, and (4) community-aware guidance through GNN-identified bridge entities and inter-community affinity scores. This multi-signal integration, particularly the bridge scoring mechanism, addresses the "echo chamber" problem where graph exploration becomes trapped in dense local communities. We formalize the autonomous discovery problem, prove theoretical properties of our scoring function, and demonstrate that beam search with multi-signal guidance achieves $O(b \cdot h)$ complexity while maintaining high recall compared to exhaustive exploration. To our knowledge, Odin represents the first autonomous discovery system deployed in regulated production environments (healthcare and insurance), demonstrating significant improvements in pattern discovery quality and analyst efficiency. Our approach maintains complete provenance traceability -- a critical requirement for regulated industries where hallucination is unacceptable.

Figures & tables

Panel of Figure 1 — Figure 1: Odin Two-Phase Architecture. Phase 1 (offline) constructs the KG and computes GNN-based community metadata. Phase 2 (online) performs real-time exploration using COMPASS scoring with bridge/affinity signals from Phase 1.

Method	Cov.@50	Paths	Time	Quality
Exhaustive	95%	125k	47s	4.3
Random Walk	68%	3k	8s	3.5
PPR-only	87%	1.9k	3.2s	3.1
GNN Embed.	52%	2.1k	4.1s	2.8
Odin	90%	1.9k	3.8s	4.2

Table 1: Experimental Results on Healthcare KG (

h=3

k=50

)

Configuration	Quality Score	Coverage@50
Full Odin (all signals)	4.2	90%
No NPLL ( $S_{\text{edge}}=1$ )	3.1	87%
No Temporal ( $S_{\text{temp}}=1$ )	4.1	89%
No Bridge ( $S_{\text{bridge}},S_{\text{affinity}}=1$ )	3.8	88%

Table 2: Ablation Study: Signal Contributions (HKG,

h=3

k=50

)

Knowledge Graphs

Knowledge graphs represent entities and relationships as structured, queryable networks for integrating data and supporting reasoning.

See all 232 papers

Sep 6, 2026

AutoKD: Autonomous Knowledge Discovery

Scientific discovery in data-rich domains is currently constrained by human bandwidth: the growth in the volume and complexity of real-world data far outpaces the rate at which researchers can read, reason, and synthesize. Recent LLM-based multi-agent systems have begun to automate portions of the research cycle, but they target hypothesis generation in settings where validation cannot itself be automated, and each run is one-shot, with no mechanism for findings to accumulate or steer subsequent inquiry. This paper introduces AutoKD, a multi-agent framework for autonomous knowledge discovery that is both computational and cumulative, allowing validated findings to persist and inform subsequent inquiry. Six coordinated LLM agents collaborate in an open-ended discovery loop, where accepted findings are stored in a persistent insight graph that serves as both long-term memory and an exploration-steering mechanism. We evaluate AutoKD on three diverse datasets from two perspectives: Open-ended Quality against published findings, and Conditioned Quality via literature-derived queries. Across both evaluation perspectives, AutoKD covers known findings and surfaces substantive discoveries that complement human-driven research. Our code is available at https://github.com/GeQinwen/AutoKD.

Qinwen Ge, Bo Ni, Haowei Fu +3

Vanderbilt University · Air Force Research Laboratory

AI Agents for Scientific Discovery Autonomous Scientific Discovery Multi-Agent LLM Systems Memory-Augmented Agents

Ask PDF

Mar 31, 2026

Nomad: Autonomous Exploration and Discovery

We introduce Nomad, a system for autonomous data exploration and insight discovery. Given a corpus of documents, databases, or other data sources, users rarely know the full set of questions, hypotheses, or connections that could be explored. As a result, query-driven question answering and prompt-driven deep-research systems remain limited by human framing and often fail to cover the broader insight space. Nomad addresses this problem with an exploration-first architecture. It constructs an explicit Exploration Map over the domain and systematically traverses it to balance breadth and depth. It generates and selects hypotheses and investigates them with an explorer agent that can use document search, web search, and database tools. Candidate insights are then checked by an independent verifier before entering a reporting pipeline that produces cited reports and higher-level meta-reports. We also present a comprehensive evaluation framework for autonomous discovery systems that measures trustworthiness, report quality, and diversity. Using corpora of selected UN and WHO reports and arXiv papers on LLM agents, we show that Nomad produces reports with strong numeric grounding, higher overall quality and actionability than baselines, and more diverse insights over several runs. Nomad is a step toward autonomous systems that not only answer user questions or conduct directed research, but also discover which questions, research directions, and insights are worth surfacing in the first place.

Bokang Jia, Samta Kamboj, Satheesh Katipomu +3

Inception, G42 · MBZUAI · G42

Autonomous Research Agents Autonomous Scientific Discovery Scientific Hypothesis Generation

Ask PDF

Oct 13, 2026

Knowledge Graphs as Files: An Agent Harness Where Tool Creation and Tool Use Co-Evolve

Searching text-rich knowledge graphs requires following relations while examining textual evidence. Predefined graph interfaces constrain what evidence agents can access, even when they write code to combine tool calls or process retrieved subgraphs. We propose direct knowledge graph interaction (DKGI), a harness in which language model agents create graph access tools directly over complete node and edge files. The agent writes Python code to follow relations, combine node sets, and select textual evidence, interleaving execution with shell search and file inspection. This lets agents process large node sets in bulk while returning selected text for the model to assess. Execution feedback guides tool creation and revision, while the evolving tools determine what evidence the agent gathers next. On benchmark datasets spanning three domains, training-free DKGI exceeds the strongest published baseline by at least 6.7 Hit@1 points on every graph, even with a minimal harness. Controlled ablations show the benefits of multi-turn programming over shell-only access and predefined graph tools, while trajectories show agents revising code to extend searches or address errors. These findings highlight the value of allowing tool creation and tool use to co-evolve during graph search. Our code and data are available at https://github.com/leopoldwhite/DKGI.

Yuyang Bai, Yu Wang, Yu Zhang

Texas A&M University · University of Georgia

Tool-Using Agents LLM Agent Harnesses Graph-Based Retrieval Knowledge Graph Question Answering

Ask PDF

Abstract

Knowledge Graphs

Explore similar work

AutoKD: Autonomous Knowledge Discovery

Nomad: Autonomous Exploration and Discovery

Knowledge Graphs as Files: An Agent Harness Where Tool Creation and Tool Use Co-Evolve