The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents

Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction.

By Tang, Wang, Zhang +17Oct 26, 2026

Score██████░░░░5.9

Caveats

Preprint; not yet peer reviewed.

VerdictWorth a reader's time today.

Read the original PDF Code

Abstract

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.

Weidong Tang, Ruiheng Wang, Jingxuan Zhang, Hexin Wang, Haoyuan Chen, Zhengfeiyang Zhang, Yixing Ma, Zichen Jiang, Ziyu Guo, Haodong Li, Zhengbo Jiao, Zhiqing Cui, Xinxiang Yin, Shuo Liang, Zhenglin Wan, Hongzhan Lin, Wangbo Zhao Kaipeng Zhang, Pengfei Zhou, Odin Zhang, Yang You

The editor's rubric

Heuristic review

Leverage3 / 5: A method or resource many groups across the field will adopt within a year.; 24% of this desk’s rubric
Magnitude3 / 5: Large gain: roughly 2x, or a clear new state of the art on a hard, unsaturated problem.; 18% of this desk’s rubric
Evidence3 / 5: Solid: multiple benchmarks or cohorts, ablations, fair baselines, released code or data.; 14% of this desk’s rubric
Novelty2 / 5: A new combination of known ideas.; 16% of this desk’s rubric
Trajectory3 / 5: A clear path to scale.; 18% of this desk’s rubric
Stakes2 / 5: Benefits a professional community (practitioners, clinicians, engineers).; 10% of this desk’s rubric

Dimension	Level	Weight	What that level means
Leverage	███░░3/5	24%	A method or resource many groups across the field will adopt within a year.
Magnitude	███░░3/5	18%	Large gain: roughly 2x, or a clear new state of the art on a hard, unsaturated problem.
Evidence	███░░3/5	14%	Solid: multiple benchmarks or cohorts, ablations, fair baselines, released code or data.
Novelty	██░░░2/5	16%	A new combination of known ideas.
Trajectory	███░░3/5	18%	A clear path to scale.
Stakes	██░░░2/5	10%	Benefits a professional community (practitioners, clinicians, engineers).

Editor’s rationale

Heuristic triage from title and abstract text only, not a reading of the paper. Cues found: method (we propose); breadth (many tasks); gains (relative gain); verification (multiple benchmarks, held-out test, experimental validation); scale (scalable); stakes (general AI).

How the score was computed

rank-2026-10-18

Score██████░░░░5.9

Score = 10 × (65% × adjusted merit / 10 + 25% × attention + 10% × freshness)

Desks place stronger verdicts first, then use this score to order work within the same verdict.

Merit: 5.5 / 10; Weighted rubric, evidence-gated.
Adjusted merit: 4.7 / 10; Shrunk toward the desk prior by editor confidence (46%).
Attention: 90%; Citations, upvotes, points, mentions.
Freshness: 60%; Half-life decay since publication.

Hugging Face upvotes297 (reference 25, via hf-daily, Oct 28, 2026, 13:49 UTC)
GitHub stars14 (reference 250, via hf-daily, Oct 28, 2026, 13:49 UTC)

The record

Reviewed by heuristic-v10 on Oct 28, 2026, 01:23 UTC. Paper type: method.
Categories: cs.AI, cs.CV
TOP, No.1 in the Artificial Intelligence edition of October 28, 2026.