Substrate-Primary Mode

What this is

Maxim has historically used a language model as the AUT's action selector — the LLM proposes the next tool call, the executor dispatches it, the bio-systems learn from the outcome. The bio-substrate (NAc, EC, ATL, Hippocampus, reflexes, Default Network) has been an augmentation layer sitting around the LLM: predicting outcomes, biasing recognition, capturing episodes, providing reactive behaviors.

Substrate-primary mode flips that. The bio-substrate becomes the action selector. The LLM is removed from the AUT's decision loop entirely and replaced with NAc.recommend_action() reading from learned causal links, reward biases, and active drive states. The action proposal flows through the same executor.execute() dispatch — but the proposer is the substrate, not a language model.

Why this exists

Three motivations:

Parallel-mode architecture, not replacement

Substrate-primary mode runs in parallel to the existing LLM-AUT path. The user-facing default does not change. There are now two operating modes for the AUT:

The orchestrator, environment NPCs, imagination designer, and Oasis distillation all continue to use LLMs. Substrate-primary mode is specifically about the AUT's action loop.

How action selection works

NAc.recommend_action() scores each available tool by combining three signals:

The highest-scoring tool above min_confidence (default 0.3) wins. Ties are resolved deterministically by tool name. If nothing scores high enough, the method returns None — substrate-primary mode never falls back to random selection. The substrate must have an opinion to act.

from maxim.decisions.nac import NAc, NACConfig

nac = NAc(NACConfig())
# ... agent has observed pick_up_food → satisfaction (positive, several times)
# ... drives indicate hunger=0.8

action = nac.recommend_action(
    agent_id="my_infant",
    available_tools=["pick_up_food", "examine_rock", "rest"],
    current_drives={"hunger": 0.8},
)
# → {"tool_name": "pick_up_food", "params": {}, "confidence": 0.74,
#    "source": "substrate-primary",
#    "reasoning": "causal_pos=0.62; drive:hunger(0.80) name-match"}

The returned dict is compatible with agents.autonomy.Proposal.action and is dispatched through the standard executor.execute() path — no new dispatcher.

Phase −1 — the gating Boolean (PASSED 2026-05-09)

The most important question in the entire substrate-primary program: can the substrate generate even one non-reflex action without LLM proposal?

If yes, the rest of the program is feasible. If no, NAc needs significant extension before substrate-primary mode is viable.

The Phase −1 prototype lands NAc.recommend_action() and 11 unit tests. All tests pass. The substrate can generate non-reflex actions from learned causal links + drive heuristics.

The next phases (still to ship):

D&D survival as the bidirectional kill criterion

A substrate-primary AUT that cannot survive a D&D-style campaign orchestrated by an LLM-DM is a failed bio-substrate. AND a simulation environment that no learning substrate can navigate is a failed simulation environment. The convergence test is mutually load-bearing:

D&D was chosen because it has long-horizon temporal structure, novel entities every session, decision-making with delayed reward, role coherence demands, and multi-agent dynamics. Cradle (current sensorimotor learning) is necessary; D&D is sufficient.

Confound discipline: raw vs primed substrate

Substrate-primary Maxims can either start from a fresh substrate (raw — the headline experimental condition) or bootstrap from accumulated experience via the Maxim Hivemind. Both are valid, but they answer different questions:

• Raw substrate demonstrates "the substrate can develop cognition from zero." Required for Phase 0 + Phase 1 validation.
• Primed substrate demonstrates "the substrate can absorb collective experience and operate." End-user convenience path; ships once Hivemind is live.

Both ship in parallel. The grounded-language plan's Phase 0 and Phase 1 specifically run with the Hivemind disabled so the headline experiment stays clean.

Pretrained-LLM crutches to disable

When running substrate-primary mode (or running the LLM-AUT path with the intent of not biasing the substrate's learning), several runtime mitigations should be turned off because they exist specifically to compensate for pretrained LLM behaviors that don't exist in a fresh substrate:

The bio-natural alternative for tool-failure avoidance already exists: NAc records tool:X → failure:not_registered with negative valence and recommend_action() subtracts that confidence from the tool's score. With the prompt-level hint disabled, the substrate's negative-valence avoidance becomes the only signal — which is exactly what we want to measure.

The crutch table grows over time. The principle: if a mitigation exists because the pretrained LLM does something the substrate hasn't earned, the substrate-only experiments must turn it off so we measure substrate competence and not the mitigation.