Implementation of the MAD-Logic framework for zero-error execution of long-horizon tasks, based on the MAKER (Massively decomposed AgenT KERnel) research paper Solving a Million-Step LLM Task with Zero Errors (arXiv:2511.09030v1).
Why use MAD-Logic? Because standard agents fail exponentially as tasks get longer.
| Feature | Standard Agent | MAD-Logic (k=7) |
|---|---|---|
| 10-Step Success | 10.74% | 99.99% |
| 100-Step Success | 0.00000002% | 99.70% |
| Reliability Gain | 1x | 9.97 Billion X |
Simulation data for 80% per-step accuracy models.
- Maximal Agentic Decomposition (MAD): Automatically breaks complex tasks into minimal subtasks to prevent reliability decay.
- First-to-ahead-by-k Voting: Uses mathematical consensus to guarantee success even with imperfect models.
- Red-Flag Filtration: Real-time monitoring to catch and discard "suspicious" outputs (hallucinations, loops, hedging).
- ASP v2.0 Compliant: Universal skill standard for any IDE or Agent (Claude Code, Cursor, etc.).
To use this framework:
-
Antigravity Agents: Place the provided
.skillfile in your~/.antigravity/skills/directory. -
Generic Agents (Claude Code / Cursor): Clone this repository and point your agent to this directory. It will detect the
SKILL.mdandscripts/automatically.
voting.py: Consensus algorithm with scaling law calculators.red_flag.py: Heuristic filters for response quality.simulation_test.py: Reproduce the paper's findings on reliability scaling.
- Sinha, S., et al. (2025). Solving a Million-Step LLM Task with Zero Errors. arXiv:2511.09030.
- ASP v2.0 Protocol