INQUIRING LINE

An AI agent's tool-picking fails not because its index is bad, but because it carves the task into the wrong-sized steps.

Why does task decomposition granularity become the bottleneck in skill routing?

This explores why the *grain size* at which a task gets broken into sub-steps — not the search index or the skill vocabulary — is what limits an agent's ability to route work to the right skills.


This explores why the *grain size* at which a task gets broken into sub-steps ends up gating everything downstream in skill routing. The core claim in the corpus is blunt: when an agent has to pick from a large library of skills, the hard part isn't matching a sub-task to a skill — it's carving the task into the right sub-tasks in the first place. Standard LLM decomposition only recovers about 34% of the correct steps, and that step-level miss rate caps how well retrieval can ever do, no matter how good the index is What blocks skill retrieval in task decomposition?. Tellingly, once you correct the step *count*, most of the gains come back — which relocates the remaining bottleneck to reranking representations rather than to vocabulary alignment. If you split too coarsely, one 'step' spans several skills and no single skill matches; too finely, and you fragment intent so no skill matches either.

The reason this matters so much is that real agent work is composition, not selection. Routing across thousands of skills is really a decompose → retrieve → compose loop: break the query into atomic sub-tasks, fetch a skill per sub-task, then assemble them into a dependency-aware plan How should agents route across thousands of skills?. Every stage after decomposition inherits its errors. Retrieval can only find skills for the sub-tasks you actually named, and the plan can only be as coherent as the boundaries you drew. So decomposition isn't one step among many — it's the step that defines the search space for all the others.

What's interesting is that the corpus suggests granularity is a *learnable, transferable* skill rather than a fixed property of the model. When you split an agent into a separate decomposer and a solver, the decomposition ability generalizes across domains while solving ability does not Does separating planning from execution improve reasoning accuracy? — evidence that knowing *how finely to cut* is a distinct competence worth training on its own. Agents can even mine reusable sub-task routines from past runs at a finer granularity than whole tasks, compounding them hierarchically for 24–51% gains Can agents learn reusable sub-task routines from past experience?. And a trained skill curator, decoupled from a frozen executor, learns to reshape a skill library toward the granularity that actually gets reused Can a separate trained curator improve skill libraries better than frozen agents?.

The counterintuitive payoff shows up at the extreme end. Push decomposition far enough — down to minimal, near-trivial subtasks with a vote at each step — and you can run million-step tasks with zero errors, and small non-reasoning models suddenly suffice where you'd expect to need a frontier model Can extreme task decomposition enable reliable execution at million-step scale?. That inverts the usual intuition: the granularity of the cut, not the raw power of the router or executor, is the lever. The same logic appears in reasoning structured as recursive subtask trees, where the right decomposition lets a single model absorb work that otherwise needs a multi-agent system Can recursive subtask trees overcome context window limits?, and in LLM-programs that hand each step only its relevant context so sub-tasks stay modular and debuggable Can algorithms control LLM reasoning better than LLMs alone?.

So the bottleneck is granularity because it sits *upstream* of matching. You can build capability vectors and sub-linear indices that make discovery scale beautifully Can semantic capability vectors replace manual agent routing?, but a perfect index over the wrong sub-tasks still routes to the wrong skills. Get the grain right and cheap models plus simple retrieval win; get it wrong and no amount of routing sophistication recovers.


Sources 9 notes

What blocks skill retrieval in task decomposition?

Standard LLM decomposition reaches only 34% step-level recall, gating retrieval success. Correcting step count recovers 75% of gains in iterative methods, shifting the bottleneck to representation-level reranking rather than vocabulary alignment.

How should agents route across thousands of skills?

Real agent tasks demand composing multiple skills rather than selecting one. The routing problem becomes decompose-retrieve-compose: break queries into atomic sub-tasks, retrieve skills per sub-task, and assemble them into dependency-aware plans.

Does separating planning from execution improve reasoning accuracy?

Modular architectures with separate decomposer and solver models outperform monolithic LLMs, with decomposition ability transferring across domains while solving ability does not. The separation prevents planning-execution interference and produces more generalizable skills.

Can agents learn reusable sub-task routines from past experience?

Agent Workflow Memory induces sub-task routines at finer granularity than full tasks, abstracts example-specific values, and compounds them hierarchically. This produces 24.6% relative gain on Mind2Web and 51.1% on WebArena, with larger gains as train-test gaps widen.

Can a separate trained curator improve skill libraries better than frozen agents?

SkillOS shows that separating a trainable curator from a frozen executor, grouped by task streams, causes skill repositories to shift from generic verbose additions toward actionable execution logic and cross-task meta-strategies. The trained curator generalizes across different executor backbones and domains.

Show all 9 sources
Can extreme task decomposition enable reliable execution at million-step scale?

MAKER solves million-step tasks with zero errors by decomposing into minimal subtasks, applying voting at each step, and flagging correlated errors. Surprisingly, small non-reasoning models suffice when decomposition is extreme enough, inverting the standard approach to hard problems.

Can recursive subtask trees overcome context window limits?

The Thread Inference Model demonstrates that reasoning structured as recursive subtask trees with rule-based KV cache pruning sustains accurate reasoning beyond context limits, even when manipulating 90% of the cache. This enables single models to replace multi-agent systems by handling full recursive reasoning internally.

Can algorithms control LLM reasoning better than LLMs alone?

LLM Programs embed LLMs within explicit algorithms that manage control flow and state, presenting only step-specific context to each LLM call. This information hiding addresses capability and context window limits while treating complex reasoning as modular, debuggable sub-tasks.

Can semantic capability vectors replace manual agent routing?

Versioned Capability Vectors embedded in HNSW indices couple semantic matching with policy and budget constraints, making capability discovery a first-class operation that scales sub-linearly as agent heterogeneity increases.

Papers this line draws on 8

The research behind the notes this line reads — ranked by how closely each paper relates.

Research prompt for your LLMexpand ↓

Copy into ChatGPT or Claude to take this line of inquiry further — it asks the model to find newer work and re-test which earlier constraints still hold.

You are a research analyst investigating a still-open question: why does task-decomposition granularity — the grain size at which a task is cut into sub-steps — become the bottleneck in skill routing across large skill libraries?

What a curated library found — and when (dated claims, not current truth). These span roughly 2024–2026:
- Standard LLM decomposition recovers only ~34% of correct steps, and that step-level miss rate caps how well any retrieval index can route, no matter how good it is (~2024).
- Correcting the step COUNT restores most of the lost gains — relocating the residual bottleneck to reranking representations, not vocabulary alignment (~2024).
- Splitting an agent into a separate decomposer and solver makes decomposition generalize across domains while solving does not — granularity looks like a distinct, trainable competence (~2024).
- Mining reusable sub-task routines below the whole-task level compounds hierarchically for 24–51% gains (~2024).
- Pushed to the extreme — near-trivial subtasks with a vote per step — you get million-step near-zero-error runs, and small non-reasoning models suffice (~2025).

Anchor papers (verify; mind their dates): Divide-or-Conquer? (arXiv:2402.15000, 2024); Agent Workflow Memory (arXiv:2409.07429, 2024); Solving a Million-Step LLM Task with Zero Errors (arXiv:2511.09030, 2025); SkillOS: Learning Skill Curation for Self-Evolving Agents (arXiv:2605.06614, 2026).

Your task:
(1) RE-TEST EACH CONSTRAINT. For every finding, judge whether newer models, training, tooling, orchestration (memory, caching, multi-agent), or evaluation have relaxed or overturned it — especially the 34% ceiling. Separate the durable question from the perishable limit; cite what resolved it and say where a constraint still holds.
(2) Surface the strongest CONTRADICTING or SUPERSEDING work from the last ~6 months — foreground disagreement over whether fine grain, learned curation, or bigger routers actually wins.
(3) Propose 2 research questions that assume the regime may have moved.
Cite arXiv IDs; flag anything you cannot ground in a real paper.