DRAFT — IN PROGRESS

Maxwell: A Thermodynamic Hypervisor for Autonomous Agents

February 2026

Abstract

Abstract will synthesize the core thesis once research is complete. Current working hypothesis: Treating compute as a scarce economic resource with thermodynamic constraints enables natural selection for useful work among autonomous agents.

Paper Outline

1. The Problem: Fairness is a Bug

  • • Why CFS (Completely Fair Scheduler) fails for autonomous agents
  • • The three pathologies: resource squatting, thermal tragedy, no natural selection
  • • Core thesis: fairness for humans ≠ fairness for agents

2. The Insight: Physics as Policy

  • • CPUs as thermodynamic systems, not abstract timesharing
  • • Price as a function of temperature and thermal headroom
  • • The feedback loop: parasites heat → price rises → parasites die

3. The Mechanism

  • • **3.1 GSP Auction:** Generalized Second-Price for compute time
  • • **3.2 Energy Wallets:** Agents earn/spend in $JOULE
  • • **3.3 Landauer's Tax:** Thermodynamic cost of memory erasure
  • • **3.4 Apoptosis:** Graceful termination at insolvency

4. The Experiment: Scientist vs. Leech

  • • Experimental design: control (Linux CFS) vs treatment (Maxwell)
  • • Agent profiles: productive (prime finding) vs parasitic (hash mining)
  • • Metrics: efficiency (primes/joule), thermal behavior, survival time
  • • Hypothesis: Maxwell achieves ≥1.8x efficiency improvement

5. Proof of Inference: Power-Trace Verification

  • • The verification problem: is the agent actually inferring?
  • • Thermodynamic fingerprinting: distinct power signatures by workload type
  • • Research validation: 89-100% accuracy distinguishing workload classes
  • • Tiered verification: power-trace → TEE → zkML

6. Applications

  • • **6.1 DePIN:** Continuous attestation for decentralized compute
  • • **6.2 Agent Fleets:** Decentralized value discovery via auction
  • • **6.3 GPU Clusters:** Filling idle cycles, 80%+ utilization

7. Related Work

  • • Economic scheduling: Spawn, Mariposa, resource markets
  • • Power-aware scheduling: RAPL, thermal governors
  • • Verifiable compute: zkML, TEE attestation, PoUW

8. Limitations and Future Work

  • • Current: single-node only, CPU focus
  • • Future: multi-node coordination, GPU integration
  • • Open questions: value discovery mechanisms, agent incentive alignment

9. Conclusion

  • • Summary of contribution
  • • When does the world need this?
  • • "Fairness is a bug; Maxwell is the fix"

Current Status

This paper is being written alongside the research documented in the research notes. Each section will be filled in as experiments are run and insights are validated. The outline above represents the target structure.