#long-horizon agents

topiclong-horizon agents

2 papers · 1 filter

cs.LG2026

TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents

Leitian Tao, Baolin Peng, Wenlin Yao +5

The paper proposes TRACE, a turn-level reward assignment method that estimates credit for each tool-call in long-horizon agents using log‑ratio state values and temporal‑difference…

cs.AI2026

Oracle Agent Memory as an Enterprise Memory Substrate for Long-Horizon AI Agents

Richmond Alake, Cesare Bernardis, Paul Cayet +10

The paper presents Oracle Agent Memory, a database-native memory layer designed to store and manage the state of long-horizon AI agents, handling ingestion, retrieval, and revision…