The Adaptive Reasoning Architecture is an open research project building a small AI that reasons in iterative steps — updating its own weights as it thinks, rather than guessing in one shot.
Standard AI models read a problem, run one forward pass, and output an answer. ARA does something fundamentally different — it reasons in steps, checks its own work, and rewrites its own memory as it thinks.
Four million parameters permanently locked after Phase 1 training. This frozen core proposes reasoning operations, checks logical coherence, and drives backtracking when contradictions appear. It never changes during inference — it is the stable mathematical conscience of the system.
Six million parameters that update in real time — during inference, while solving a problem. This workspace holds intermediate state, absorbs retrieved knowledge from external libraries, and builds a self-organising memory hierarchy: free scratch space, procedural skills, and consolidated intuition.
Instead of one forward pass, ARA runs up to 1,000 micro-iterations per problem. Each iteration proposes a step, checks it, accepts or backtracks, and updates the plastic weights. Harder problems naturally get more iterations — something a fixed-depth Transformer fundamentally cannot do.
Standard models use 50–70% of their capacity to store facts. ARA stores nothing — it retrieves what it needs on demand. All 10M parameters go to reasoning. Knowledge gaps trigger structured queries that progressively deepen in specificity until the model can proceed.
8 Transformer layers, d_model=128, d_ff=512. Every weight matrix is partitioned per-neuron — not per-layer. 204 frozen neurons and 307 plastic neurons coexist in every FFN.
ARA does not output an answer from a single forward pass. It runs an algorithm — one micro-iteration at a time — until the problem is solved or the budget is exhausted.
The input problem is converted to a symbolic state s₀ — a set of variable bindings and assertions. The backtrack stack is initialised. Plastic weights reset to baseline.
The frozen reasoning core selects the most likely next operation from 25+ mathematical primitives given the current state. No weights change here — this is pure forward inference through the core.
The proposed new state s_t' is evaluated for logical consistency against all prior assertions. If any contradiction exists, the step is rejected. This is a symbolic checker — fast and deterministic.
Coherent step: accept s_t, update plastic weights via the coherence loss, increment resistance on active neurons. Contradiction: roll back, reduce resistance, pop the stack, reset the learning rate.
When progress stalls for 10 consecutive iterations, the core detects a knowledge gap and queries the external library. The retrieved content is absorbed into the plastic workspace via 3–5 gradient steps.
If h(s_t, s_goal) = 0, the solution is complete. If the iteration budget T_max is exhausted, the best partial solution is returned with its coherence score. The entire loop runs in ~120MB of memory.
The ARA Hub is where the team thinks, builds, and ships together. Here is everything inside and how to navigate it.
The ARA Mathematical Companion derives all architecture claims from first principles — from high-school algebra through gradient descent and EWC. Here are the four core equations that govern the system.
Only the 60% plastic neurons receive gradient updates. The ⊙ (Hadamard product) with the binary mask M_plastic ensures the frozen core is mathematically untouchable — not suppressed, never updated.
Drives real-time plastic weight updates. Two components: consistency (how likely is this state under the model's own distribution?) and progress (how many subgoals remain?). μ₁=0.6, μ₂=0.4.
Fisher-weighted springs resist overwriting neurons already proven useful. Resistance Rᵢ grows with each successful use (+0.02) and shrinks on failure (−0.05). Self-organises into three memory tiers.
At T=1000 iterations, β=0.5, f_facts=0.6: a 10M model reaches ~775M parameter-equivalents. This is the theoretical ceiling the Shadow Demo is built to test empirically.
The Shadow Demo is at the empirical threshold. The mathematics are coherent. The architecture is specified. Now it needs engineers, researchers, and builders to make it real. If you are drawn to small models with big ideas — come help build the ARA.