Field-Theoretic Memory for AI Agents
Continuous Dynamics for Context Preservation
New Accepted at ICLR 2026 · AI WILD Research
Open research lab · AI agent reliability
Research
you can
run.
Rotalabs studies how AI agents fail when they act in the world — and builds the benchmarks, probes, monitors, and protocols to measure it. Every result is published, installable, and reproducible from the raw trajectories up.
Open source · Pre-registered protocols · Reproducible from saved runs
Pre-registered audit · null resultPreprint — coming soon
GlassBox: a cross-pattern audit of linear probe gates.
A surface-clean paired-twin benchmark for irreversible banking actions, testing whether residual-stream probes can separate substantively wrong actions from legitimate twins under cross-pattern transfer.
24 cases · 4 patterns · 5 model families
Across three evaluable open-weight families, the linear probe showed no cross-pattern edge over a default-prompted judge. We publish the whole audit — including where our own method fails: paper, benchmark, trajectories, trained probes, and pipeline. The point is the protocol.
BenchmarkTrajectoriesAudit pipeline
Flagship study — coming soon
GlassBox is not a claim. It is an instrument.
A benchmark, a protocol, and a reusable audit framework for testing monitors that gate irreversible agentic actions. It is designed to be re-run, challenged, and extended — a concrete research surface, not just a position statement.
FindingA pre-registered null: no operating point in the layer sweep yields a separating boundary on unseen patterns. We report it rather than bury it.
BenchmarkSurface-clean paired twins across wrong-action patterns, explicitly measuring false escalation rather than hiding it.
ProtocolLeave-one-pattern-out evaluation, net-of-false-escalation scoring, and a pre-registered credit gate.
ReleasePaper, dataset, trajectories, probes, and audit code — published under the Rotalabs research distribution.
Research program
Nine fronts on agent reliability.
Interpretability probes, adversarial testing, verification, evaluation science, steering, and trust propagation — released as papers and installable methods through 2026.
01
Agent Reliability
Papers Q1 2026 Detection and verification for autonomous AI. Methods to identify when agents hallucinate, fail, or strategically underperform.
02
AI Evaluation Science
Papers Q1 2026 Adversarial evaluation methods that resist gaming. Benchmarks that detect hidden capabilities and strategic behavior.
03
Memory Systems
Published Field-theoretic memory treating stored information as continuous fields governed by PDEs — semantic diffusion, thermodynamic decay, and multi-agent field coupling.
04
Reasoning Verification
Papers Q1 2026 Verifying AI outputs without ground truth. Methods for code, plans, and decisions from reasoning models like o3 and R1.
05
Interpretability
Active Practical interpretability for production. Not "understand the model" but "should I trust this output?"
06
Multi-Agent Trust
Active Trust dynamics when agents coordinate with agents. Propagation, verification, and failure modes in multi-agent systems.
07
Adversarial Robustness for Agents
Active Attack taxonomies, detection, and defenses for agentic AI — beyond prompt injection: tool poisoning, memory corruption, planning attacks, and coordination exploits.
08
Uncertainty Quantification
Active Calibrated confidence for AI decision support. Activation-based uncertainty estimation, propagation through reasoning chains, and calibration without ground truth.
09
World Models & Physical AI
Active Beyond language models: AI that understands and predicts the physical world. World models, embodied reasoning, simulation, and physics-aware AI.
Research distribution
Papers are only half the interface.
Rotalabs publishes installable packages so methods can be inspected, reproduced, and embedded into new experiments — all 12 on PyPI and npm, AGPL-3.0.
$ pip install rotalabs-probe
$ pip install rotalabs-redqueen
$ pip install rotalabs-verity
$ pip install rotalabs-eval
# probes · adversarial testing · verification · evaluation
rotalabs-context
Context intelligence for AI agents.
rotalabs-probe
Sandbagging detection via activation probes.
rotalabs-steer
Steering vectors for runtime behavior control.
rotalabs-verity
Neuro-symbolic verified code synthesis.
rotalabs-cascade
Trust-based decision routing.
Recent papers 02 03 04
Published, preprint, in progress.
Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety
Semantic MAP-Elites red-teaming across frontier LLMs
Verity: Neuro-Symbolic Synthesis of Verified Distributed Systems
CE2P translates formal-verification failures into structured LLM feedback. The benefit is inversely correlated with model capability — weaker...
From the blog
Notes from the lab.
May 31, 2026 Mar 01, 2026 Feb 18, 2026
Evolutionary Adversarial Testing for AI Systems with Red Queen
Red-teaming that evolves its own attacks. rotalabs-redqueen uses quality-diversity search to discover diverse jailbreaks across single-turn, multi-turn, and agentic/MCP surfaces — reproducibly, and as...
Field-Theoretic Memory for AI Agents
We treat agent memory as continuous fields governed by partial differential equations instead of discrete database entries. The result: +116% F1 on multi-session reasoning...
Shared Context for AI Agents: Introducing rotalabs-context
AI agents that can't share what they know make the same mistakes independently. We're releasing rotalabs-context - a context intelligence engine for ingesting, searching,...
Credibility is not claimed. It is released — and open to be broken.Rotalabs operating principle
Enterprise
Rotalabs is our open research lab. The methods behind this work are available to enterprises as products and consulting through Rotascale →