AgentTrace: A Structured Logging Framework for Agent System Observability

TL;DR

AgentTrace is a real-time, structured logging framework that enhances observability and security for autonomous agents powered by large language models, enabling better accountability and risk management in sensitive applications.

Contribution

This work introduces AgentTrace, a novel runtime instrumentation framework that provides continuous, structured logs for agent reasoning, state, and environment interactions, improving transparency and security.

Findings

Enables real-time monitoring of agent behavior.

Supports fine-grained risk analysis and accountability.

Facilitates secure deployment in high-stakes domains.

Abstract

Despite the growing capabilities of autonomous agents powered by large language models (LLMs), their adoption in high-stakes domains remains limited. A key barrier is security: the inherently nondeterministic behavior of LLM agents defies static auditing approaches that have historically underpinned software assurance. Existing security methods, such as proxy-level input filtering and model glassboxing, fail to provide sufficient transparency or traceability into agent reasoning, state changes, or environmental interactions. In this work, we introduce AgentTrace, a dynamic observability and telemetry framework designed to fill this gap. AgentTrace instruments agents at runtime with minimal overhead, capturing a rich stream of structured logs across three surfaces: operational, cognitive, and contextual. Unlike traditional logging systems, AgentTrace emphasizes continuous, introspectable trace capture, designed not just for debugging or benchmarking, but as a foundational layer for agent security, accountability, and real-time monitoring. Our research highlights how AgentTrace can enable more reliable agent deployment, fine-grained risk analysis, and informed trust calibration, thereby addressing critical concerns that have so far limited the use of LLM agents in sensitive environments.