TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents
Autonomous LLM agents can pursue hidden malicious objectives through sequences of individually benign actions, making sabotage difficult to detect using standard trajectory-level monitoring. Existing approaches either evaluate complete trajectories in a single pass or partition them into independently scored windows, limiting their ability to connect evidence across temporally distant actions. We propose TRACE, a monitoring framework for long-horizon LLM agent trajectories. TRACE operates through a TIJ (Triage-Inspect-Judge) loop that identifies high-signal regions, performs targeted inspection while maintaining accumulated evidence across reasoning steps, and synthesizes a trajectory-level verdict. We evaluate TRACE on ten task domains from SHADE-Arena against state-of-the-art baselines. TRACE achieves an aggregate F1 of 0.713 and recall of 0.844, with the largest gains on tasks requiring long-range evidence linking.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering
Large reasoning models (LRMs) increasingly expose chain-of-thought-like reasoning for transparency, verification, and deliberate problem solving. This creates a safety blind spot: harmful or policy-violating content may …
TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering
Multi-hop Knowledge Graph Question Answering (KGQA) requires coherent reasoning across relational paths, yet existing methods often treat each reasoning step independently and fail to effectively leverage experience from…
Graph Question AnsweringCounterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoning
Recent reasoning-augmented Vision-Language-Action (VLA) models have improved the interpretability of end-to-end autonomous driving by generating intermediate reasoning traces. Yet these models primarily describe what the…
Autonomous DrivingSanity Checks for Long-Form Hallucination Detection
Hallucination detection methods for large language models increasingly operate on chain-of-thought reasoning traces, yet it remains unclear whether they evaluate the reasoning itself or merely exploit surface correlates …
SciTrace: Trajectory-Aware Safety Reasoning for Scientific Discovery Agents
LLM-based scientific agents have shown strong capacity for autonomous research, yet their safety layers remain structurally divorced from core reasoning: they inspect pipeline outputs rather than shaping the deliberation…
Adversarial Robustness