Paper · Research automation
Infinity Machine
Infinity Machine: a self-improving AI agent for researchA self-improving research agent that autonomously modifies its own harness to solve and verify open problems in quantum information.
The loop
An AI agent modifies its own harness, prompts, and meta agent to solve and verify open scientific problems. These modifications pass through a kernel-enforced gate and are directly used by the agent to conduct further autonomous research.
The loop
Infinity Machine- Agent solves open scientific problems
- Agent modifies its own harness
- Kernel verifies modifications via checks
- Agent uses new harness for research
- Agent solves open scientific problems
- Agent modifies its own harness
- Kernel verifies modifications via checks
- Agent uses new harness for research
↻ The improved system does the next round, and the loop turns again.
Why it is a road to recursion
Allowing an agent to edit its own harness and meta-agent provides a direct path to recursive self-improvement in research capabilities.
Evidence
Produced four results beyond the published state of the art on catalogued open problems in quantum information.
research-agentharness-evolutionquantum-information
Related loops
More research automation →
autoresearch
- Coding agent edits LLM training script
- Runs a 5-minute training job
- Keeps change if validation improves
- Changes transferred to larger models
- repeat
Research automationAndrej Karpathy · 2026
SplatLab
- SplatLab reproduces 3DGS baselines
- proposes and codes extensions
- scores candidates via Elo tournament
- uses feedback to refine research outputs
- repeat
Research automationSeemandhar Jain et al. · 2026
FreeEvolve
- Agent evolver automates workflow design
- Scores candidate skills on target agents
- Improves its own evolution skill
- Produces better target agents
- repeat
Research automationLecheng Kong et al. · 2026