splitting-task-across-several-agents-helps-long-horizon-tasks-whose CLM-0325mechanismsingle paperReviewed by AI
Splitting a task across several agents helps on long-horizon tasks whose parts depend on each other sparsely, and hurts on tightly coupled sequential workflows, where generic multi-agent methods fall below a single-agent harness because decomposition fragments the dependency chain and coordination overhead outweighs the context isolation it buys; as single agents improve the collaboration benefit shrinks.
Capability: Getting more from several models than from one
Observed on
Long-horizon agent benchmarks split into sparsely and densely coupled sets, 2026; comparison of single-agent harnesses with generic multi-agent variants and the authors' SAIGE grap.
Sources
- Method paper with a diagnostic framing; the dependency-structure boundary is the reusable claim, and it agrees with the geometry result below (weak models gain, strong models often do not).
Either way, bring evidence: a link, or what you saw.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- For teams of up to 50 heterogeneous embodied LLM agents in simulated wildfire missions, building the manager hierarchy per mission so that concurrently executable work sits under a parallel-allocating manager and prerequisite-chained work under a phase-advancing manager beats fixed decentralized, single-planner, and hybrid coordination architectures on mission score and on progress accumulated per step, and the advantage does not depend on which base language model is used.Getting more from several models than from one · reviewed by AI
- Across 41 models and seven multi-agent benchmarks, gains in single-agent capability translate only weakly into multi-agent competence (understanding other agents, joint planning, efficient communication, adaptation); on the multi-agent planning task accuracy rose only about 30% across a family's full scale range, so coordination ability does not emerge from scaling alone and needs its own data and training.Getting more from several models than from one · reviewed by AI
- For CAE simulation tasks (OpenFOAM, FEniCS, PyChrono, COMSOL) run with a current general-purpose coding-agent harness and a strong backbone, a single agent with no multi-agent role decomposition and no scripted self-critique matches or exceeds the published scores of multi-agent specialized CAE systems, because the harness itself supplies the multi-turn reasoning and execution-feedback repair the decomposition was built to compensate for.Getting more from several models than from one · reviewed by AI
- When initially identical LLM agents act in a shared persistent world where their artifacts remain and are scored by an external simulator, the shared society builds broader and more resilient technology portfolios than a matched best-of-N population of isolated agents, but isolated search still yields the single best-performing artifact.Getting more from several models than from one · reviewed by AI
- In multi-agent literature-synthesis pipelines, most of the gain over a fixed role-based pipeline comes from the shared-workspace architecture and the added critique/dissemination actions rather than from learning the coordination policy: on OARelatedWork, a learned decentralized RL controller scored 3.82 overall versus 3.80 for a centralized LLM coordinator given the same workspace and action space, while a naive orchestrator without that architecture scored 3.40.Getting more from several models than from one · reviewed by AI
Notes
Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: medium. Falsifier as drafted: A multi-agent method that beats a matched single-agent harness on densely coupled sequential tasks at equal token budget.