Alignment in Time: Peak-Aware Orchestration for Long-Horizon Agentic Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908842945675264 |
|---|---|
| author | Shi, Hanjing DiFranzo, Dominic |
| author_facet | Shi, Hanjing DiFranzo, Dominic |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_17910 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Alignment in Time: Peak-Aware Orchestration for Long-Horizon Agentic Systems Shi, Hanjing DiFranzo, Dominic Artificial Intelligence 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. |
| title | Alignment in Time: Peak-Aware Orchestration for Long-Horizon Agentic Systems |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.17910 |