PreAct-Bench: Benchmarking Predictive Monitoring in LLMs

• URL: http://arxiv.org/abs/2606.09890v1
• Date: Wed, 03 Jun 2026 13:26:41 GMT
• Title: PreAct-Bench: Benchmarking Predictive Monitoring in LLMs
• Abstract summary: We study a critical yet overlooked safety task, which we term Predictive Monitoring.<n>Can a model infer whether it will culminate in an unethical action before the overt action is executed?<n>We present PreActBench, a benchmark of 1,000 paired ethical and unethical action trajectories spanning five domains.<n>Results show that while humans achieve promising performance, predictive monitoring remains challenging even for strong models.
• Score: 36.98978443442419
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents capable of executing multi-step action trajectories toward a given objective. While existing safety research has focused on detecting unethical behavior from complete trajectories, this paradigm is fundamentally retrospective: it identifies harm only after it has already occurred. In this work, we study a critical yet overlooked safety task, which we term Predictive Monitoring: given only a partial action trajectory, can a model infer whether it will culminate in an unethical action before the overt action is executed? To support this task, we present PreActBench, a benchmark of 1,000 paired ethical and unethical action trajectories spanning five domains. We evaluate a range of LLMs, safety guardrail models, and latent probing methods across varying fractions of the action trajectory using our Prefix Foresight F1 metric. Results show that while humans achieve promising performance, predictive monitoring remains challenging even for strong models, highlighting the need for future-oriented risk reasoning in LLM safety.

Related papers

• SchemeArena: Factorized Stress Testing of Scheming in LLM Agents [15.436206398870986]
  Key factors in scheming include instrumental goals, environmental affordances, oversight conditions, and perceived consequences.<n>SCHEMEARENA is a 400-scenario benchmark for scalable scheming stress testing.<n>SCOUT is a scheming monitor that grounds judgments in evidence drawn from agents' reasoning and actions.
  arXiv  Detail & Related papers  (2026-09-08T02:02:51Z)
• Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics [42.27928681606673]
  Large Reasoning Models (LRMs) introduce new opportunities for safety monitoring through their Chain of Thought (CoT) reasoning.<n>We investigate the hidden representations of LRMs to determine whether future behavior can be predicted from prompt and CoT representations.<n>We find that future model behavior is more distinguishable when examined over the full trajectory than from a single static prediction.
  arXiv  Detail & Related papers  (2026-05-18T15:29:04Z)
• Seeing Farther and Smarter: Value-Guided Multi-Path Reflection for VLM Policy Optimization [41.15414881730464]
  Vision-Language Models (VLMs) offer a general perceive-reason-act framework for this goal.<n>Previous approaches rely on inefficient and often inaccurate implicit learning of state-values from noisy foresight predictions.<n>We propose a novel test-time computation framework that decouples state evaluation from action generation.
  arXiv  Detail & Related papers  (2026-02-22T22:53:16Z)
• Detecting Object Tracking Failure via Sequential Hypothesis Testing [80.7891291021747]
  Real-time online object tracking in videos constitutes a core task in computer vision.<n>We propose interpreting object tracking as a sequential hypothesis test, wherein evidence for or against tracking failures is gradually accumulated over time.<n>We propose both supervised and unsupervised variants by leveraging either ground-truth or solely internal tracking information.
  arXiv  Detail & Related papers  (2026-02-13T14:57:15Z)
• ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs [48.50397204177239]
  As large language models (LLMs) evolve, evaluating the safety of their actions becomes critical.<n>We introduce ManagerBench, a benchmark that evaluates LLM decision-making in realistic, human-validated managerial scenarios.<n>A parallel control set, where potential harm is directed only at inanimate objects, measures a model's pragmatism and identifies its tendency to be overly safe.
  arXiv  Detail & Related papers  (2025-10-01T13:08:33Z)
• Saffron-1: Safety Inference Scaling [69.61130284742353]
  SAFFRON is a novel inference scaling paradigm tailored explicitly for safety assurance.<n>Central to our approach is the introduction of a multifurcation reward model (MRM) that significantly reduces the required number of reward model evaluations.<n>We publicly release our trained multifurcation reward model (Saffron-1) and the accompanying token-level safety reward dataset (Safety4M)
  arXiv  Detail & Related papers  (2025-06-06T18:05:45Z)
• Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives [52.863024096759816]
  Misaligned research objectives have hindered progress in adversarial robustness research over the past decade.<n>We argue that realigned objectives are necessary for meaningful progress in adversarial alignment.
  arXiv  Detail & Related papers  (2025-02-17T15:28:40Z)
• Deception in LLMs: Self-Preservation and Autonomous Goals in Large Language Models [0.0]
  Recent advances in Large Language Models have incorporated planning and reasoning capabilities.<n>This has reduced errors in mathematical and logical tasks while improving accuracy.<n>Our study examines DeepSeek R1, a model trained to output reasoning tokens similar to OpenAI's o1.
  arXiv  Detail & Related papers  (2025-01-27T21:26:37Z)
• Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models [79.76293901420146]
  Large Language Models (LLMs) are employed across various high-stakes domains, where the reliability of their outputs is crucial. Our research investigates the fragility of uncertainty estimation and explores potential attacks. We demonstrate that an attacker can embed a backdoor in LLMs, which, when activated by a specific trigger in the input, manipulates the model's uncertainty without affecting the final output.
  arXiv  Detail & Related papers  (2024-07-15T23:41:11Z)

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.