The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents
The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents
The Trinity framework improves multi-modal agent performance by organizing tasks into capability trees, generating simulated training worlds, routing professional Harness modules, and recursively refining multi-modal agents, achieving a mean performance improvement of 34 and 26 points on 28 training benchmarks and 18 unseen benchmarks, including two real-world embodied tasks.
Published on Oct 26
Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Abstract
The Trinity framework recursively improves multimodal agents by organizing tasks into a capability tree, generating simulated training worlds, and routing specialized harness modules to boost performance on diverse benchmarks.
Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing heterogeneous, verifiable environments is costly, and manual Harness iteration cannot keep pace with growing task diversity and complexity. A key insight is that tasks with different modalities and surface forms can share the same underlying capability requirements. We therefore introduce The Trinity, a recursive self-improvement framework coupling world generation with Harness evolution through three roles: Creator, Explorer, and Evolver. Drawing on verified execution trajectories, Evolver shifts the basis of task organization from surface categories to shared requirements, reorganizing the original task tree into a hierarchical capability tree. We introduce Capability-Driven Real2Sim2Real: for heterogeneous tasks at the same node, Creator abstracts their common requirements into simplified, verifiable simulated worlds for capability learning, while evaluation on original tasks measures transfer. Along this capability tree, Explorer progressively evolves reusable capability modules through selective inheritance, forming a Harness tree whose validated updates accumulate across iterations within a fixed topology. The resulting Harnesses specialize in different capabilities, motivating a Capability-Aware Harness Router that uses public task information to select compatible module configurations from the tree. Our evolved Harnesses improve mean performance by 34 points across 28 training benchmarks and 26 points across 18 unseen benchmarks, including two real-world embodied tasks.
View arXiv page View PDF Add to collection
Get this paper in your agent:
hf papers read 2610.36077
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.36077 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.36077 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.36077 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
Source: Hugging Face Daily Papers · huggingface.co