# Representation Transitions Reveal Emerging Safety Risks in Multi-Turn LLM Agents

arXiv: https://arxiv.org/abs/2610.00400 · HTML: https://mlsanity.com/paper/2610.00400/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 31 of its 39 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 30 of 31)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents](https://mlsanity.com/paper/2410.09024/) (2024)
- [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024)
- [R-Judge: Benchmarking Safety Risk Awareness for LLM Agents](https://mlsanity.com/paper/2401.10019/) (2024)
- [Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models](https://mlsanity.com/paper/2312.14197/) (2023)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [ShieldGemma: Generative AI Content Moderation Based on Gemma](https://mlsanity.com/paper/2407.21772/) (2024)
- [AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents](https://mlsanity.com/paper/2503.18666/) (2025)
- [Qwen3Guard Technical Report](https://mlsanity.com/paper/2510.14276/) (2025)
- [ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning](https://mlsanity.com/paper/2503.22738/) (2025)
- [GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning](https://mlsanity.com/paper/2406.09187/) (2024)
- [Transformers need glasses! Information over-squashing in language tasks](https://mlsanity.com/paper/2406.04267/) (2024)
- [Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents](https://mlsanity.com/paper/2602.13379/) (2026)
- [ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction](https://mlsanity.com/paper/2508.00500/) (2025)
- [RvLLM: LLM Runtime Verification with Domain Knowledge](https://mlsanity.com/paper/2505.18585/) (2025)
- [Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs](https://mlsanity.com/paper/2512.08417/) (2025)
- [TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling](https://mlsanity.com/paper/2605.27690/) (2026)

## Built on by (most cited first, 1 of 1)

- [Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models](https://mlsanity.com/paper/2610.11773/) (2026)

## Abstract (arXiv)

Multi-turn attacks on agentic systems can compose individually permissible actions into harmful outcomes, challenging defenses that assess actions or states in isolation. We show that such attacks leave a detectable signature in the agent's internal representations: harmful behavior emerges as an accumulated representation transition across context updates, whose triggering context can be identified from the same signal. We further find that naive aggregation is confounded by benign representation drift, as a contrastive safety direction need not assign zero to benign transitions. We address this by denoising the direction, anchoring benign traffic at zero and removing its leading variation directions, with no runtime cost. These findings motivate DART, a runtime framework that detects and attributes representation shifts and intervenes with targeted reminders. Across six models and two multi-turn benchmarks, DART reduces attack success from 84% to 25% on MT-AgentRisk, catching every attack at a mean false-alarm rate of 12%, and from 97% to 52% on ASEval, at costs in benign non-refusal of 8% and 0%, respectively. On MT-AgentRisk, it outperforms ToolShield, the state-of-the-art multi-turn defense, on all six models: under the same protocol, ToolShield reaches only 55%. Denoising is critical: on ASEval, the undenoised monitor catches only 7%-40% of attacks, while the denoised monitor catches 60%-85%. The same monitor covers single-turn indirect injection without modification and adds only 0.14-0.56 s overhead per monitored step without requiring an auxiliary model, making it a lightweight complement to computation-heavy speculative defenses.