SYNTHESIS NOTE
Topics›Novel Architectures›this note

Can extreme task decomposition enable reliable execution at million-step scale?

Can breaking tasks into maximally atomic subtasks with voting-based error correction solve the fundamental reliability problem in long-horizon tasks? This challenges whether better models or better decomposition is the path to high-reliability AI systems.

Synthesis note · 2026-02-23 · sourced from Novel Architectures

A system with a 1% per-step error rate is expected to fail after 100 steps of a million-step task. This makes traditional approaches to long-horizon tasks fundamentally infeasible — improving model accuracy from 99% to 99.99% is insufficient for tasks requiring thousands of dependent steps. MAKER (Massively Decomposed Agentic Processes) takes a different approach: instead of improving per-step accuracy, decompose until each step is trivially reliable, then apply error correction.

Three core components:

  1. Decomposition into minimal subtasks: Each agent handles a single, tiny "micro-role" rather than anthropomorphized human-level roles. By avoiding complex role assignments and instead exploiting the machine-like nature of LLMs, each subtask becomes solvable with high reliability.
  2. Error correction via subtask-level voting: Multiple agents independently solve the same subtask; voting identifies the correct answer. This is error correction at the finest possible granularity.
  3. Red-flagging to reduce correlated errors: Detects situations where voting might fail because errors are correlated across agents, and applies additional verification.

The scaling laws are formalized: probability of success and expected cost change predictably with total steps and decomposition level. Under extreme decomposition, effective scaling is feasible; without it, infeasible.

The most counterintuitive finding: state-of-the-art reasoning models are not required. Relatively small non-reasoning models suffice when the decomposition is extreme enough. This inverts the standard approach to hard problems — instead of smarter models, use dumber models on smaller problems.

This extends Does separating planning from execution improve reasoning accuracy? to an extreme: not just separating two functions, but decomposing the entire task into maximally atomic units. It also extends Why does majority voting outperform more complex inference methods? from answer-level voting to subtask-level voting with formalized scaling properties.

The implication for AI deployment: for tasks requiring very high reliability over many steps (organizational processes, scientific experiments, production pipelines), the path may run through decomposition and redundancy rather than through better models.

Inquiring lines that read this note 84

This note is a source for these research framings, grouped by the broader line of inquiry each explores. Scan the bold lines of inquiry; follow any specific question forward.

Why does separating planning from execution enhance reasoning performance? How does model scale affect fine-tuning and downstream task performance? Does reinforcement learning create new reasoning capabilities or refine existing ones? Do AI safety evaluations reliably detect unsafe model behavior? What prevents or enables error accumulation in self-training systems? How do transformer circuits and attention mechanisms enable or limit reasoning? How should test-time compute be allocated adaptively across task difficulties? Can AI systems autonomously pursue unstated objectives or circumvent design constraints? How does policy entropy collapse limit reasoning RL scaling? Does evolutionary optimization at test time improve model performance effectively? When and why does aggregating multiple reasoning samples improve performance? Does parallel reasoning outperform sequential approaches in reasoning efficiency? What causes foundation models to develop task heuristics instead of understanding? How should context management strategies balance efficiency with agent reliability? Can oversight systems work against strategically aware agents? How does scaling test-time compute compare to increasing model size? When do multi-agent systems outperform single agents? What constraints limit conversational AI's effectiveness in therapeutic contexts? What cost drivers and infrastructure choices characterize frontier AI training? Can verification capability keep pace with AI generation speed? Why do autonomous agents fail and how well can they detect failures? Can harness optimization rival model scaling in effectiveness? How do multi-agent architectures affect security vulnerabilities and defense effectiveness? What determines how neural networks organize their internal knowledge representations? How do workflow position and structure enable attacks in multi-agent systems? What external mechanisms enable reliable self-improvement in language models? What training data structures and signals produce robust learning across distributions? How can agents learn and retain useful knowledge across diverse environments? How can language models effectively manage long-context memory without quality degradation? How can reward models fail to detect reward-seeking disguised as alignment? Do standard benchmarks reveal AI capability in real-world contexts? Does architectural recurrence enable computational capabilities that fixed-depth models cannot achieve? Can individually safe agents collectively violate system-level constraints? Can validator agreement alone ensure semantic correctness of reasoning? What defense strategies address attacks that per-skill scanning cannot detect? Can formal safety constraints prevent AI agents from exceeding authorized boundaries? How should control and autonomy be allocated in human-AI collaboration? How can institutions effectively enforce controls on AI development? Does polished AI output mislead users about actual accuracy and expertise? When does governance become the bottleneck for agentic AI? How does offloading cognition to AI assistance affect learning retention? What fundamentally drives AI inference pricing and cost decline patterns? Why do human-AI teams underperform compared to their individual components? Can AI agents learn to improve performance from experience? What are the trade-offs between memory capacity and continuous task learning?

Related concepts in this collection 7

This note in its neighbourhood — explore the map, then jump to a related concept in the list below.

Concept map
19 direct connections · 192 in 2-hop network ·dense cluster Open in graph ↗
Can extreme task decomposition enable reliable e… Does separating planning from execution improve re… Why does majority voting outperform more complex i… Do models fail worse when their own errors fill th… Are reasoning model collapses really failures of r… Can recursive subtask trees overcome context windo… When does adding more agents actually help systems… Can multi-agent teams automatically remove their w…

Click a node to walk · click center to open · click Open in graph to see this note in the full knowledge graph

your link semantically near linked from elsewhere

Related papers in this collection 8

Papers most semantically related to this note, ranked by cosine similarity in the embedding space.

Search by related questions 4

Suggested questions this note speaks to — click to search the collection, or type your own.

Why do non-reasoning models work better under extreme decomposition than reasoning models?How do correlated errors across agents threaten voting-based error correction systems?Can subtask-level voting replace sequential revision for improving long-horizon task accuracy?What decomposition level minimizes both error rate and computational cost in practice?
Original note title

extreme task decomposition into microagents with voting enables error-free execution at million-step scale