TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents

• URL: http://arxiv.org/abs/2606.07054v1
• Date: Fri, 05 Jun 2026 08:54:38 GMT
• Title: TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents
• Abstract summary: LLM agents can pursue hidden malicious objectives through sequences of individually benign actions.<n>Existing approaches either evaluate complete trajectories in a single pass or partition them into independently scored windows.<n>We propose TRACE, a monitoring framework for long-horizon LLM agent trajectories.
• Score: 62.969415789328025
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Revisiting Complete Reasoning Traces for Post-Training [61.76889440384448]
  Large language models (LLMs) are often post-trained on pre-collected reasoning trajectories to improve their reasoning capability.<n>We show that full trajectories provide only limited benefit, while partial trajectories are effective even under heavy truncation.
  arXiv  Detail & Related papers  (2026-09-07T06:46:17Z)
• Agent-ToM: Learning to Monitor Autonomous LLM Agents via Theory-of-Mind Reasoning [11.914433611519359]
  Monitoring autonomous large language model (LLM) agents for covert malicious behavior is challenging due to delayed, context-dependent, and long-horizon attack patterns.<n>We propose textbfAgent-ToM, a learning-to-monitor framework grounded in Theory-of-Mind (ToM) reasoning for security analysis of autonomous agents.
  arXiv  Detail & Related papers  (2026-05-22T20:57:20Z)
• Beyond Input Guardrails: Reconstructing Cross-Agent Semantic Flows for Execution-Aware Attack Detection [32.301679396929536]
  We propose SysName, a framework that shifts the defensive paradigm from static input filtering to execution-aware analysis.<n>SysName synthesizes fragmented operational primitives into contiguous behavioral trajectories, enabling a holistic view of system activity.<n> Empirical evaluations demonstrate that SysName effectively detects over ten distinct compound attack vectors, achieving F1-scores of 85.3% and 66.7% for node-level and path-level end-to-end attack detection, respectively.
  arXiv  Detail & Related papers  (2026-03-04T01:59:16Z)
• DRAFT: Task Decoupled Latent Reasoning for Agent Safety [59.46137757545185]
  We propose DRAFT (Task Decoupled Latent Reasoning for Agent Safety), a latent reasoning framework that decouples safety judgment into two trainable stages.<n>An Extractor distills the full trajectory into a compact continuous latent draft, and a Reasoner that jointly attends to the draft and the original trajectory to predict safety.<n>DRAFT consistently outperforms strong baselines, improving accuracy from 63.27% (LoRA) to 91.18% averaged over benchmarks.
  arXiv  Detail & Related papers  (2026-02-11T07:45:14Z)
• TrajAD: Trajectory Anomaly Detection for Trustworthy LLM Agents [47.147717604167376]
  Trajectory Anomaly Detection essential for enabling efficient rollback-and-retry.<n>General-purpose LLMs struggle to identify and localize these anomalies.<n>We propose TrajAD, a specialized verifier trained with fine-grained process supervision.
  arXiv  Detail & Related papers  (2026-02-06T07:13:49Z)
• RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents [144.5598958575922]
  Re-TRAC is an agentic framework that performs cross-trajectory exploration.<n>We show that Re-TRAC consistently outperforms ReAct by 15-20% on BrowseComp with frontier LLMs.
  arXiv  Detail & Related papers  (2026-02-02T18:58:07Z)
• Tracking by Detection and Query: An Efficient End-to-End Framework for Multi-Object Tracking [23.800994163971502]
  Multi-object tracking (MOT) is dominated by two paradigms: tracking-by-detection (TBD) and tracking-by-query (TBQ)<n>We propose TBDQ-Net, a unified tracking-by-detection-and-query (TBDQ) framework that effectively combines the strengths of both paradigms.<n>Our method efficiently integrates pretrained, high-performance detectors with an MOT-tailored associator.
  arXiv  Detail & Related papers  (2024-11-09T14:38:08Z)
• MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking [56.92165669843006]
  We propose MotionTrack, which learns robust short-term and long-term motions in a unified framework to associate trajectories from a short to long range. For dense crowds, we design a novel Interaction Module to learn interaction-aware motions from short-term trajectories, which can estimate the complex movement of each target. For extreme occlusions, we build a novel Refind Module to learn reliable long-term motions from the target's history trajectory, which can link the interrupted trajectory with its corresponding detection.
  arXiv  Detail & Related papers  (2023-03-18T12:38:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.