Research

Paper

AI LLM March 04, 2026

Robustness of Agentic AI Systems via Adversarially-Aligned Jacobian Regularization

Authors

Furkan Mumcu, Yasin Yilmaz

Abstract

As Large Language Models (LLMs) transition into autonomous multi-agent ecosystems, robust minimax training becomes essential yet remains prone to instability when highly non-linear policies induce extreme local curvature in the inner maximization. Standard remedies that enforce global Jacobian bounds are overly conservative, suppressing sensitivity in all directions and inducing a large Price of Robustness. We introduce Adversarially-Aligned Jacobian Regularization (AAJR), a trajectory-aligned approach that controls sensitivity strictly along adversarial ascent directions. We prove that AAJR yields a strictly larger admissible policy class than global constraints under mild conditions, implying a weakly smaller approximation gap and reduced nominal performance degradation. Furthermore, we derive step-size conditions under which AAJR controls effective smoothness along optimization trajectories and ensures inner-loop stability. These results provide a structural theory for agentic robustness that decouples minimax stability from global expressivity restrictions.

Metadata

arXiv ID: 2603.04378
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-03-04
Fetched: 2026-03-05 06:06

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.04378v1</id>\n    <title>Robustness of Agentic AI Systems via Adversarially-Aligned Jacobian Regularization</title>\n    <updated>2026-03-04T18:41:45Z</updated>\n    <link href='https://arxiv.org/abs/2603.04378v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.04378v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>As Large Language Models (LLMs) transition into autonomous multi-agent ecosystems, robust minimax training becomes essential yet remains prone to instability when highly non-linear policies induce extreme local curvature in the inner maximization. Standard remedies that enforce global Jacobian bounds are overly conservative, suppressing sensitivity in all directions and inducing a large Price of Robustness. We introduce Adversarially-Aligned Jacobian Regularization (AAJR), a trajectory-aligned approach that controls sensitivity strictly along adversarial ascent directions. We prove that AAJR yields a strictly larger admissible policy class than global constraints under mild conditions, implying a weakly smaller approximation gap and reduced nominal performance degradation. Furthermore, we derive step-size conditions under which AAJR controls effective smoothness along optimization trajectories and ensures inner-loop stability. These results provide a structural theory for agentic robustness that decouples minimax stability from global expressivity restrictions.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CR'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.MA'/>\n    <published>2026-03-04T18:41:45Z</published>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Furkan Mumcu</name>\n    </author>\n    <author>\n      <name>Yasin Yilmaz</name>\n    </author>\n  </entry>"
}