Research

Paper

AI LLM February 20, 2026

Alignment in Time: Peak-Aware Orchestration for Long-Horizon Agentic Systems

Authors

Hanjing Shi, Dominic DiFranzo

Abstract

Traditional AI alignment primarily focuses on individual model outputs; however, autonomous agents in long-horizon workflows require sustained reliability across entire interaction trajectories. We introduce APEMO (Affect-aware Peak-End Modulation for Orchestration), a runtime scheduling layer that optimizes computational allocation under fixed budgets by operationalizing temporal-affective signals. Instead of modifying model weights, APEMO detects trajectory instability through behavioral proxies and targets repairs at critical segments, such as peak moments and endings. Evaluation across multi-agent simulations and LLM-based planner--executor flows demonstrates that APEMO consistently enhances trajectory-level quality and reuse probability over structural orchestrators. Our results reframe alignment as a temporal control problem, offering a resilient engineering pathway for the development of long-horizon agentic systems.

Metadata

arXiv ID: 2602.17910
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-02-20
Fetched: 2026-02-23 05:33

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.17910v1</id>\n    <title>Alignment in Time: Peak-Aware Orchestration for Long-Horizon Agentic Systems</title>\n    <updated>2026-02-20T00:16:07Z</updated>\n    <link href='https://arxiv.org/abs/2602.17910v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.17910v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Traditional AI alignment primarily focuses on individual model outputs; however, autonomous agents in long-horizon workflows require sustained reliability across entire interaction trajectories. We introduce APEMO (Affect-aware Peak-End Modulation for Orchestration), a runtime scheduling layer that optimizes computational allocation under fixed budgets by operationalizing temporal-affective signals. Instead of modifying model weights, APEMO detects trajectory instability through behavioral proxies and targets repairs at critical segments, such as peak moments and endings. Evaluation across multi-agent simulations and LLM-based planner--executor flows demonstrates that APEMO consistently enhances trajectory-level quality and reuse probability over structural orchestrators. Our results reframe alignment as a temporal control problem, offering a resilient engineering pathway for the development of long-horizon agentic systems.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-02-20T00:16:07Z</published>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Hanjing Shi</name>\n    </author>\n    <author>\n      <name>Dominic DiFranzo</name>\n    </author>\n  </entry>"
}