Research Area
Governed Agent Systems
Research and architecture treating governance as runtime behaviour: receipts, provenance, evaluation gates and execution boundaries that turn agentic output into auditable delivery.
Works in this area (4)
-
PreprintEmpirical StudyGoverned Local Experiment
Bounded Recursive Self-Improvement Under Human Governance: Evidence from a Seven-Cycle Reinforcement Learning Contour Experiment
A bounded seven-cycle scaffolding-level experiment reporting four promoted states, one retained failed transition, and two NO_CHANGE outcomes under separate human promotion authority. It does not establish AGI, unbounded improvement, autonomous promotion, or external production validation.
-
PreprintConceptual Framework
The Reinforcement Learning Contour: From Document Production to Governed Epistemic Transformation in AI-Assisted Scientific Inquiry
Generative artificial intelligence has sharply reduced the technical cost of producing scientific text. Increased production capacity does not, however, entail cumulative knowledge, conceptual novelty, or epistemic progress. This paper introduces the Reinforcement Learning Contour (RLC) as a conceptual and architectural framework for shifting AI-assisted research from repetitive content generation toward governed recursive learning… Version note: current registry metadata is Version 2; the archived PDF and this summary preserve Version 1.
-
PreprintEmpirical StudySynthetic Controlled Pilot
Measuring What Survives: Pressure-Filtered Persistence and a Masking Index for LLM-Agent Safety Evaluation
When a safety intervention lowers an agent’s attack-success rate, two different things may have happened: the intervention removed a load-bearing failure route, or the agent learned the measured attacks while the route survived. Frequency metrics are necessary, but they do not by themselves…
-
PreprintEmpirical StudySynthetic Controlled Pilot
A Topological Robustness and Anti-Fragility Framework for LLM Agents
Adversarial evaluation of large-language-model agents is usually expressed as event counts: attack-success rate, policy-violation rate, refusal-failure rate, pass percentage, or robustness score. These measures are necessary, but they do not show whether a safety intervention removed a load-bearing…