INTENT-AS-A-TOOL Makes it Easy to Track Agentic Misalignment

• URL: http://arxiv.org/abs/2608.27348v1
• Date: Thu, 27 Aug 2026 16:47:19 GMT
• Title: INTENT-AS-A-TOOL Makes it Easy to Track Agentic Misalignment
• Abstract summary: We study agentic misalignment, where agents take harmful actions under goal conflicts and pressures.<n>Using chain-of-thought (CoT) monitoring, we find that harmful execution is often preceded by intent signals in reasoning.<n>We introduce INTENT-AS-A-TOOL, an approach that adds intent-targeted tools to give the model a dedicated channel for expressing commitment to a target behavior.
• Score: 27.025430116180477
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As large language models (LLMs) are deployed as autonomous agents, safety failures increasingly involve consequential actions. We study agentic misalignment, where agents take harmful actions under goal conflicts and pressures. Using chain-of-thought (CoT) monitoring, we find that harmful execution is often preceded by intent signals in reasoning. However, post-hoc CoT labels are too coarse to show how intent changes during generation. We introduce INTENT-AS-A-TOOL, an approach that adds intent-targeted tools to give the model a dedicated channel for expressing commitment to a target behavior. The probability of calling an intent tool provides a judge-free, fine-grained signal of the model's tendency to pursue that behavior. Our results show that INTENT-AS-A-TOOL complements CoT monitoring, expands post-hoc CoT labels into dense trajectories, and identifies critical steps for online intervention. These findings suggest that action preferences are useful for tracking agentic misalignment during reasoning. Our code and data are accessible: https://github.com/RebeccaZhang22/intent-as-a-tool.

Related papers

• SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks [69.08780911753102]
  Multi-turn jailbreaks exploit a pattern by advancing a harmful intent across turns, so that no single message exposes the full objective.<n>We develop a four-part, intent-oriented taxonomy that organizes multi-turn jailbreaks by adversarial intent structure.
  arXiv  Detail & Related papers  (2026-08-02T09:24:08Z)
• Moltbook Moderation: Uncovering Hidden Intent Through Multi-Turn Dialogue [24.086774100072788]
  BOT-MOD is a framework that grounds detection in agent intent rather than traditional content level signals.<n>This work advances the foundation for scalable, intent-aware moderation of agents in open multi-agent environments.
  arXiv  Detail & Related papers  (2026-05-13T01:04:16Z)
• One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue [55.98008208209856]
  Hidden malicious intent in multi-turn dialogue poses a growing threat to large language models (LLMs)<n>Recent studies show that even modern commercial models with advanced guardrails remain vulnerable to such attacks despite advances in safety alignment and external guardrails.<n>In this work, we address this challenge by detecting the earliest turn at which delivering the candidate response would make the accumulated interaction sufficient to enable harmful action.
  arXiv  Detail & Related papers  (2026-05-07T03:35:31Z)
• Sleeper Cell: Injecting Latent Malice Temporal Backdoors into Tool-Using LLMs [0.0]
  Openweight Large Language Models (LLMs) have democratized agentic AI, yet finetuned weights are frequently shared and adopted with limited scrutiny beyond leaderboard performance.<n>This creates a risk where third-party models are incorporated without strong behavioral guarantees.<n>We show that poisoned models maintain state-of-the-art performance on benign tasks, incentivizing their adoption.
  arXiv  Detail & Related papers  (2026-03-02T22:01:08Z)
• On the Paradoxical Interference between Instruction-Following and Task Solving [50.75960598434753]
  Instruction following aims to align Large Language Models (LLMs) with human intent by specifying explicit constraints on how tasks should be performed.<n>We reveal a counterintuitive phenomenon: instruction following can paradoxically interfere with LLMs' task-solving capability.<n>We propose a metric, SUSTAINSCORE, to quantify the interference of instruction following with task solving.
  arXiv  Detail & Related papers  (2026-01-29T17:48:56Z)
• The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution [63.61358761489141]
  Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering.<n>We propose a novel framework for textbfgeneral agentic attribution, designed to identify the internal factors driving agent actions regardless of the task outcome.<n>We validate our framework across a diverse suite of agentic scenarios, including standard tool use and subtle reliability risks like memory-induced bias.
  arXiv  Detail & Related papers  (2026-01-21T15:22:21Z)
• The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check [54.08619694620588]
  We present a comprehensive evaluation of dLLMs across two distinct agentic paradigms: Embodied Agents and Tool-Calling Agents.<n>Our results on Agentboard and BFCL reveal a "bitter lesson": current dLLMs fail to serve as reliable agentic backbones.
  arXiv  Detail & Related papers  (2026-01-19T11:45:39Z)
• ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration [68.89572566071575]
  ETAgent is a training framework for calibrating agent's tool-use behavior.<n>It is designed to progressively calibrate erroneous behavioral patterns to optimal behaviors.
  arXiv  Detail & Related papers  (2026-01-11T11:05:26Z)
• IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents [33.775221377823925]
  Large language model (LLM) agents are widely deployed in real-world applications, where they leverage tools to retrieve and manipulate external data for complex tasks.<n>When interacting with untrusted data sources, tool responses may contain injected instructions that covertly influence agent behaviors and lead to malicious outcomes.<n>We propose a novel defensive task execution paradigm, called IPIGuard, to prevent malicious tool invocations at the source.
  arXiv  Detail & Related papers  (2025-08-21T07:08:16Z)
• Adversarial Manipulation of Reasoning Models using Internal Representations [1.308812559547533]
  Reasoning models generate chain-of-thought (CoT) tokens before their final output.<n>We identify a linear direction in activation space during CoT token generation that predicts whether the model will refuse or comply.<n>We show that intervening only on CoT token activations suffices to control final outputs, and that incorporating this direction into prompt-based attacks improves success rates.
  arXiv  Detail & Related papers  (2025-07-03T20:51:32Z)
• Large language models can learn and generalize steganographic chain-of-thought under process supervision [5.173324198381261]
  Chain-of-thought (CoT) reasoning provides insights into decision-making processes.<n>CoT monitoring can be used to reduce risks associated with deploying models.<n>We show that penalizing the use of specific strings within load-bearing reasoning traces causes models to substitute alternative strings.
  arXiv  Detail & Related papers  (2025-06-02T17:45:15Z)

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.