Dalek: A Constructive Agent Machine
cs.AI
Submitted: 2026-09-03
Updated: 2026-09-03
Code: https://github.com/deepseek-ai/deepseek-harness
License: http://creativecommons.org/licenses/by/4.0/
The gist: We present Dalek, a closed machine designed for agents that realizes self-maintenance, self-evolution, self-reproduction, and self-organization on any substrate satisfying a general host contract.
Terminology
Abstract
We present Dalek, a closed machine designed for agents that realizes self-maintenance, self-evolution, self-reproduction, and self-organization on any substrate satisfying a general host contract. The machine is built from three primitives---actors, messages, and channels. Four obligations---a host boundary, a construction language, admissible transitions, and rule heredity---give its boundary, identity, and closure a structural basis. Von Neumann's 1948 self-reproducing automaton supplies a hereditary constructional core: a self-description together with a constructor, a copier, and a controller. Dalek combines this core with the four obligations and rederives its medium for a text-and-message agent substrate, adding explicit structures for boundary, identity, history, and growth. A large language model and a compiler occupy the payload position and form a general capability producer. New capabilities are authored, compiled, installed into the description, and inherited by descendants. The same path produces the machine's own organs and even its runtime, closing heredity and evolution within the machine.
Sources
- L2MAC: Large Language Model Automatic Computer for Extensive Code Generation
- Meta n: Recursive Self-Improvement through Emergent Depth
- Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecture
- Building LLM Agents by Incorporating Insights from Computer Systems
- Bounded Recursive Self-Improvement
- Rethinking the Evaluation of Harness Evolution for Agents
- Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces
- Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation
- Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
- Hyperagents
- Self-Reference in Large Language Models: The Introspection Threshold for Recursive Self-Improvement
- Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection