TrajectoryDB is envisioned, a trajectory-native data management system that co-designs ingestion, storage, and query processing to efficiently manage and analyze agent execution trajectories.
Abstract
AI agents generate rich execution trajectories that capture their interactions with large language models, tools, and external environments. These trajectories are increasingly valuable for downstream tasks such as memory extraction, model fine-tuning, runtime optimization, and security and cost monitoring. Yet trajectory data today is fragmented across files, databases, and observability systems, with no persistent data management system designed around its unique structure and access patterns. We argue that trajectories should be treated as a distinct data type. A trajectory combines hierarchical execution structure, large volumes of text whose analysis often requires semantic reasoning, and rich dependencies and lineage among events, intermediate states, and derived artifacts. These properties introduce new requirements throughout the data lifecycle. Ingestion must reconstruct and preserve execution structure and lineage; storage must efficiently organize large but highly redundant contexts while maintaining relationships among records; and query processing must jointly reason over structure, temporal order, semantics, and lineage. We therefore envision TrajectoryDB, a trajectory-native data management system that co-designs ingestion, storage, and query processing to efficiently manage and analyze agent execution trajectories.
Terminal-Universe is introduced, a framework which turns each trajectory into a reusable environment and explores it for synthesizing new tasks and continued interactions, and produces 37.3k task-sufficient environments.
Jie Wu, Zhen-Ru Zhang, Bei-Chen Zhang et al.· 5 citations
A two-week trace of 11.7 million requests from a large-scale production platform for general-purpose agents, backed by inference infrastructure comprising over 10k GPUs is analyzed to characterize the platform at three connected levels: task-level initiation semantics, workflow-level execution patterns, and infrastruct...
Experimental results show that RUPA consistently outperforms existing UQ methods by providing more accurate uncertainty estimates, enabling earlier failure detection, and improving uncertainty-guided agent execution across diverse agent tasks.
This paper examines Data Agents from a harness-centric perspective, introducing a taxonomy of Data Agents and associated data environments, and identifying four open reliability problems: inactive semantic calibration, missing clarification, missing experience transfer, and the missing verification-repair repository.
Hua-Chi Zhou, Yu-Jing Zhang, Jia-He Du et al.· 0 citations
This work introduces latent equivalence learning, a identity-factorized, query-conditioned routing system that materializes the relevant dataset-specific evidence for downstream reasoning, allowing the agent to operate over an already organized evidential state rather than reconstructing cross-schema structure at every...
Results show that entity-structured indexing and episode-level provenance provide a reliable foundation for long-term memory in agents, and EnSIMem achieves high answer accuracy while maintaining compact, evidence-focused contexts.
Xuan-Yu Meng, Xing Fan, Xin-Yi Fan et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.