Working Paper: Towards a Category-theoretic Comparative Framework for Artificial General Intelligence
arXiv:2603.28906v1 Announce Type: new Abstract: AGI has become the Holly Grail of AI with the promise of level intelligence and the major Tech companies around the world are investing unprecedented amounts of resources in its pursuit. Yet, there does not exist a single formal definition and only some empirical AGI benchmarking frameworks currently exist. The main purpose of this paper is to develop a general, algebraic and category theoretic framework for describing, comparing and analysing different possible AGI architectures. Thus, this Category theoretic formalization would also allow to compare different possible candidate AGI architectures, such as, RL, Universal AI, Active Inference, CRL, Schema based Learning, etc. It will allow to unambiguously expose their commonalities and differ
View PDF HTML (experimental)
Abstract:AGI has become the Holly Grail of AI with the promise of level intelligence and the major Tech companies around the world are investing unprecedented amounts of resources in its pursuit. Yet, there does not exist a single formal definition and only some empirical AGI benchmarking frameworks currently exist. The main purpose of this paper is to develop a general, algebraic and category theoretic framework for describing, comparing and analysing different possible AGI architectures. Thus, this Category theoretic formalization would also allow to compare different possible candidate AGI architectures, such as, RL, Universal AI, Active Inference, CRL, Schema based Learning, etc. It will allow to unambiguously expose their commonalities and differences, and what is even more important, expose areas for future research. From the applied Category theoretic point of view, we take as inspiration Machines in a Category to provide a modern view of AGI Architectures in a Category. More specifically, this first position paper provides, on one hand, a first exercise on RL, Causal RL and SBL Architectures in a Category, and on the other hand, it is a first step on a broader research program that seeks to provide a unified formal foundation for AGI systems, integrating architectural structure, informational organization, agent realization, agent and environment interaction, behavioural development over time, and the empirical evaluation of properties. This framework is also intended to support the definition of architectural properties, both syntactic and informational, as well as semantic properties of agents and their assessment in environments with explicitly characterized features. We claim that Category Theory and AGI will have a very symbiotic relation.
Comments: 37 pages, 7 figures, 1 table
Subjects:
Artificial Intelligence (cs.AI)
Cite as: arXiv:2603.28906 [cs.AI]
(or arXiv:2603.28906v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2603.28906
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Pablo De Los Riscos [view email] [v1] Mon, 30 Mar 2026 18:34:27 UTC (315 KB)
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
benchmarkannouncefeature
The new Storm Radar app is a treasure trove of data for weather nerds
The horrible winter of 2026 is behind us in New England; now we’ve moved on to the season where there’s a threat of rain basically every day. Given that, the updated Storm Radar app from The Weather Company (owners of the Weather Channel app) caught my eye. There are tons of good weather apps out there, and I’m the kind of nerd that likes to try them all, and Storm Radar feels pretty unique to me. The main interface is, as you’d expect, your local radar. Tapping on any point of the map calls up a detailed forecast for that exact point, with data coming via The Weather Company’s “gridded forecast on demand” (FOD) system. The default view is precipitation, but there are multiple other layers you can add including temperature, cloud cover, nearby lighting strikes, wind and so forth. There are
The end of 'shadow AI' at enterprises? Kilo launches KiloClaw for Organizations to enable secure AI agents at scale
As generative AI matures from a novelty into a workplace staple, a new friction point has emerged: the "shadow AI" or "Bring Your Own AI (BYOAI)" crisis. Much like the unsanctioned use of personal devices in years past, developers and knowledge workers are increasingly deploying autonomous agents on personal infrastructure to manage their professional workflows. "Our journey with Kilo Claw has been to make it easier and easier and more accessible to folks," says Kilo co-founder Scott Breitenother. Today, the company dedicated to providing a portable, multi-model, cloud-based AI coding environment is moving to formalize this "shadow AI" layer: it's launching KiloClaw for Organizations and KiloClaw Chat, a suite of tools designed to provide enterprise-grade governance over personal AI a
A Code Authorship Analysis on the Claude Code Leak. What Was Found Doesn't Match Human or AI Code.
<p>On March 31, 2026, Anthropic shipped a source map in their npm package, exposing 514,000 lines of TypeScript. Thousands of developers analyzed it. They found feature flags, a pet system, undercover mode, and a frustration regex.</p> <p>Nobody analyzed the <strong>authorship pattern</strong> of the code itself.</p> <p>Curia is an evidence-accumulating prediction system built for unrelated research. It turned out to be exactly the right tool to ask a question nobody was asking: does this code look like it was written by humans?</p> <p>The numbers are real. What they mean is up to you.</p> <h2> The Fingerprint </h2> <p>30+ metrics were extracted from every TypeScript file and compared across codebases spanning two eras:</p> <div class="table-wrapper-paragraph"><table> <thead> <tr> <th>Code
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Research Papers
AI Inspires New Research Topics In Materials Science - miragenews.com
<a href="https://news.google.com/rss/articles/CBMihwFBVV95cUxQRlVFdkRBaHRvYkJJdFRlMTZmajEzeFRPU0hGWWdfbi02V1FnTUdVQ2pmY2VZLUV2NlB4V3BFdEVlSVZkUlhRSTZaNWFKMmcyWXJYbnNqbUhMTmp0NnFtMEppOXlPZkJSNHJfck5VSEVYcmUtX1k2QkJlR1BvUEdTTkp3UmlYRkk?oc=5" target="_blank">AI Inspires New Research Topics In Materials Science</a> <font color="#6f6f6f">miragenews.com</font>
From brain scans to alloys: Teaching AI to make sense of complex research data - Penn State University
<a href="https://news.google.com/rss/articles/CBMiwAFBVV95cUxPZDFHdkptQ2VUM2hmWjhqQkxoRnBiTWoxMXRRR21MUG5TamdUMlFRWmhvYVNHaFVNREVKU3VmSnVOdDVZYnNLb2ppYXRVRTZmVFVMV1pLTlVhUm9ybTNZbGtvZTdIMnIyMHNpOEk5aU9TSmxxS2Y4V2MwazYwY3JlX1Axbk1nd3pfcWhFdUJaaDJWRXJaMFIyTTROcmFHeXI3ZzFudXJ2M1h6UHI1LW1Ca1dta2RkM3BiYndocGk3Yjg?oc=5" target="_blank">From brain scans to alloys: Teaching AI to make sense of complex research data</a> <font color="#6f6f6f">Penn State University</font>
Locating Risk: Task Designers and the Challenge of Risk Disclosure in RAI Content Work
arXiv:2505.24246v4 Announce Type: replace Abstract: As AI systems are increasingly tested and deployed in open-ended and high-stakes domains, crowdworkers are often tasked with responsible AI (RAI) content work. These tasks include labeling violent content, moderating disturbing text, or simulating harmful behavior for red teaming exercises to shape AI system behaviors. While prior research efforts have highlighted the risks to worker well-being associated with RAI content work, far less attention has been paid to how these risks are communicated to workers by task designers or individuals who design and post RAI tasks. Existing transparency frameworks and guidelines, such as model cards, datasheets, and crowdworksheets, focus on documenting model information and dataset collection process
Togedule: Scheduling Meetings with Large Language Models and Adaptive Representations of Group Availability
arXiv:2505.01000v5 Announce Type: replace Abstract: Scheduling is a perennial-and often challenging-problem for many groups. Existing tools are mostly static, showing an identical set of choices to everyone, regardless of the current status of attendees' inputs and preferences. In this paper, we propose Togedule, an adaptive scheduling tool that uses large language models to dynamically adjust the pool of choices and their presentation format. With the initial prototype, we conducted a formative study (N=10) and identified the potential benefits and risks of such an adaptive scheduling tool. Then, after enhancing the system, we conducted two controlled experiments, one each for attendees and organizers (total N=66). For each experiment, we compared scheduling with verbal messages, shared c
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!