# Research | 2πarc at Rexzen

Source: https://rexzen.si/research/

Rexzen2πarcResearch
Research

Adaptive world models, memory, and decisions. Explore the prototypes, manuscripts, and evidence behind each line of work.
ManuscriptsEOS programCurrent questionReleased software

Research at 2πarc

We study how models represent their environments, compare predictions with observations, and decide when to update.

Released prototype

Rex-WM Micro

Question. Can a small model adapt when simulated dynamics change?

Approach. Predict one-dimensional motion, observe the next state, and compare a learned correction, retained corrections, and recent-history inference.

Scope. Local CPU release. Retained corrections have shown mixed results against short-history inference in the inspected setting.

        Recorded run and scopeSource and weights

Proposed architecture

EOS

Question. What evidence and authority should a model need to make a lasting change?

Approach. Keep prediction, inquiry, candidate updates, and commitment separate. Test a candidate on fresh evidence before it becomes persistent.

Scope. Architecture hypothesis and bounded component studies. EOS-F1 is an ongoing research track.

        Programme and statusManuscript summary

Manuscripts and methods

Evidence and decisions

Question. When can evidence distinguish a new mechanism or justify a change that affects decisions?

Approach. Formal analysis and constrained studies of state refinement, structural novelty, consequence auditing, and endorsement.

Scope. The assumptions and evidence differ by manuscript. Summaries are public and PDF access uses the existing shared password.

        Manuscript directoryAbout 2πarc

Synthetic traces illustrate how a difference between prediction and observation can prompt a review.

Adaptation and memory

Adaptive world models maintain and revise representations of changing environments. Continual learning asks how to incorporate new evidence while retaining useful earlier knowledge.

We are interested in how structured memory and explicit reasoning can work alongside learned representations. Neuromorphic and unconventional computing are longer-term exploratory directions.

Questions in the work
Pause themesPREDICTION
What happens next?

Compare prediction with observation.
MEMORY
What should a model keep?

Study adaptation and earlier learning.
EVIDENCE
What justifies a change?

State assumptions and inspect the alternatives.
Released prototypeCurrent questionManuscripts

RESEARCH PAPERS
Manuscripts

Selected manuscripts, ordered by relevance to our current research. Read a summary here, then unlock the PDF with the shared password.
Unlock PDFs
PDFs are locked.

JavaScript is needed to unlock the PDFs. You can read every title and summary without it.

01

World models · Adaptation

Adaptation, Recall and Inference under Sensor Noise

Aman Agarwal · Version 2 · 6 pages
Research manuscript

A controlled comparison of retained models, online corrections and recent-history inference when measurements are noisy and earlier conditions return.

Scope and version

Development experiments in one-dimensional simulation. The retained model bank does not show a consistent advantage over short-history inference.

Author affiliation: 2πarc, Rexzen.
Read PDFDownload PDF

02

World models · Model growth

Conditional Evidence for Persistent Model Growth

Aman Agarwal · Version 2 · 6 pages
Research manuscript

What evidence should a model need before adding a new mechanism? This paper separates prediction errors, diagnostic evidence and lasting changes to model structure.

Scope and version

Theory under stated observation laws, with reconstructed synthetic results. The saved studies were inspected rather than independently rerun.

Author affiliation: 2πarc, Rexzen.
Read PDFDownload PDF

03

EOS · World model architecture

Evidence-Gated Causal World Models for Continual General Intelligence

Aman Agarwal · Complete portfolio extract · 5 pages
Research manuscript

A proposed architecture separating high-capacity prediction from the evidence that permits persistent change. It connects world models, memory, active experiments and structural governance.

Scope and version

An architecture hypothesis, with component evidence and proposed falsification experiments. The complete system remains unimplemented. The complete five-page paper is extracted from portfolio pages 11 to 15, including its references.

Author affiliation: Sonne Systems.
Read PDFDownload PDF

04

EOS · Evidence and governance

Dual Governance for Continual Agents: Separating Reversible Information Acquisition from Persistent Self-Modification

Aman Agarwal · Complete portfolio extract · 3 pages
Research manuscript

A typed interface that gives reversible information gathering and persistent model changes different authority. Evidence for an observation cannot automatically permit a lasting mutation.

Scope and version

Formal analysis and three constrained reference studies with supplied binary mechanisms. This does not establish autonomous structural discovery or a learned open-world model. The complete three-page paper is extracted from portfolio pages 8 to 10, including its references.

Author affiliation: Sonne Systems.
Read PDFDownload PDF

05

World models · Partial observation

Consequence-Certified State Refinement and Anytime False-Birth Control in POMDP World Models

Aman Agarwal · Supplied manuscript · 7 pages
Research manuscript

When a model cannot see the full state, which histories can it safely merge? The paper studies consequences of actions and the evidence needed to create new structure.

Scope and version

Formal conditions and separate component studies. The experiments do not establish a complete POMDP agent.

Author affiliation: Sonne Systems.
Read PDFDownload PDF

06

World models · Identifiability

When Is Structural Novelty Identifiable? Consequence Separation and Anytime-Valid Model Growth

Aman Agarwal · Supplied manuscript · 6 pages
Research manuscript

A mathematical account of when available observations and interventions can distinguish a new mechanism from a known one.

Scope and version

Results depend on finite, supplied mechanism classes and exact predictive laws. These assumptions limit transfer to learned real-world systems.

Author affiliation: Sonne Systems.
Read PDFDownload PDF

07

Decision systems · Consequence auditing

Counterexamples, Not Certificates: Fresh Evidence for Learned Consequence-Query Auditing

Aman Agarwal · Complete portfolio extract · 3 pages
Research manuscript

A learned auditor can find a context where a model change causes harm. Fresh evidence checks that counterexample, while an unsuccessful search leaves the question open.

Scope and version

Synthetic auditing study with a fixed-design result. The complete three-page paper is extracted from portfolio pages 5 to 7, including its references.

Author affiliation: Sonne Systems.
Read PDFDownload PDF

08

Decision systems · Goals

Goal Endorsement Under Uncertain Authorship: Identification, Regret, and the Cost of Asking Again

Aman Agarwal · Revised manuscript · 22 pages
Research manuscript

A goal's origin and its present value are different questions. This paper studies ambiguous reports, the cost of asking again and decisions under uncertain endorsement.

Scope and version

Formal analysis, synthetic comparisons and an exploratory public-data audit. The data provide no gold standard for a person's true endorsement.

Author affiliation: Independent Researcher, Sonne Systems.
Read PDFDownload PDF

09

Foundations · Prediction

Determinism, Temporal Extension, and the Limits of Prediction

Aman Agarwal · Current manuscript · 18 pages
Research manuscript

A framework separating unique forward evolution, the possible extent of the past and the information an observer needs to predict what happens next.

Scope and version

Mathematical constructions and computational audits. The results do not determine the physical universe's history or fundamental determinism.

Author affiliation: Independent Researcher, Sonne Systems.
Read PDFDownload PDF

CURRENT QUESTION · IN PROGRESS
Current research

When conditions return, can a model use what it learned earlier to predict more accurately?

We compare this approach with models that use recent measurements. We consider noisy observations, changing conditions and the cost of each method.

The sensor-noise and model-growth manuscripts above describe the current evidence and its limits.

RELEASED SOFTWARE · 0.1.0
Rex-WM Micro

A research prototype for one-dimensional simulated motion. Source code, trained weights and a recorded example are included. It runs locally on CPU.

The recorded example does not establish a benchmark lead or performance in other environments.
Inspect the prototype
