AI Paper Atlas

Research map / Large language models / Agents, code and math

Trinity: An Evolved LLM Coordinator

Jinglue Xu, Qi Sun, Peter Schwendeman, Stefan Nielsen, Edoardo Cetin, Yujin Tang

ICLR 2026 · Large language models › Agents, code and math · approach: LLMs for optimization and heuristics · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add singular value fine-tuning of the coordinator SLM (ablation)Trinity · In-distribution averageaverage score: 67.85 -> 70.44Improved
add thinker-role selection (ablation)Trinity · In-distribution averageaverage score: 68.69 -> 70.44Improved
add tri-role selection (ablation)Trinity · In-distribution averageaverage score: 67.02 -> 70.44Improved
add tri-role selection (ablation)Trinity · MATH500accuracy: 82.00 -> 88.00Improved
use penultimate token instead of last token for hidden state (ablation)Trinity · In-distribution averageaverage score: 64.66 -> 70.44Improved
use penultimate token instead of last token (ablation)Trinity · LiveCodeBenchpass@1 (%): 50.85 -> 61.46Improved
add agent selection to role selection (ablation)Trinity · In-distribution averageaverage score: 65.95 -> 70.44Improved
use linear head instead of low-rank head (ablation)Trinity · MATH500accuracy: 0.770 -> 0.880Improved
use sparse head instead of linear head (ablation)Trinity · MMLUaccuracy: 0.916 -> 0.917No clear effect
use sep-CMA-ES instead of REINFORCE (ablation)Trinity · LiveCodeBenchpass@1: 0.253 -> 0.615Improved
use sep-CMA-ES instead of SFT (ablation)Trinity · MATH500accuracy: 0.786 -> 0.880Improved
use sep-CMA-ES instead of random search (ablation)Trinity · RLPRaccuracy: 0.345 -> 0.401Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy