# Position: Stop Acting Like Language Model Agents Are Normal Agents arXiv: https://arxiv.org/abs/2502.10420 ยท HTML: https://mlsanity.com/paper/2502.10420/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. - Builds on 52 of its 137 references that are in the map. - First posted on arXiv 4 Feb 2025. ## Placed in - LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/) ## Builds on (most cited first, 30 of 52) - [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022) - [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023) - [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023) - [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023) - [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022) - [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023) - [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023) - [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023) - [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022) - [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023) - [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023) - [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023) - [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024) - [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024) - [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023) - [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024) - [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022) - [A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis](https://mlsanity.com/paper/2307.12856/) (2023) - [ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities](https://mlsanity.com/paper/2408.04682/) (2024) - [AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments](https://mlsanity.com/paper/2405.07960/) (2024) - [PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts](https://mlsanity.com/paper/2306.04528/) (2023) - [AI Agents That Matter](https://mlsanity.com/paper/2407.01502/) (2024) - [Foundational Challenges in Assuring Alignment and Safety of Large Language Models](https://mlsanity.com/paper/2404.09932/) (2024) - [The Illusion of State in State-Space Models](https://mlsanity.com/paper/2404.08819/) (2024) - [FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design](https://mlsanity.com/paper/2311.13743/) (2023) - [Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models](https://mlsanity.com/paper/2408.08926/) (2024) - [Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast](https://mlsanity.com/paper/2402.08567/) (2024) - [The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediations](https://mlsanity.com/paper/2310.04988/) (2023) - [From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought](https://mlsanity.com/paper/2306.12672/) (2023) - [Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models](https://mlsanity.com/paper/2411.14257/) (2024) ## Built on by (most cited first, 5 of 5) - [Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective](https://mlsanity.com/paper/2504.03255/) (2025) - [Agent Identity Evals: Measuring Agentic Identity](https://mlsanity.com/paper/2507.17257/) (2025) - [Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms](https://mlsanity.com/paper/2605.30169/) (2026) - [Time, Identity and Consciousness in Language Model Agents](https://mlsanity.com/paper/2603.09043/) (2026) - [What the F*ck Is Artificial General Intelligence?](https://mlsanity.com/paper/2503.23923/) (2025) ## Abstract (arXiv) Language Model Agents (LMAs) are increasingly treated as capable of autonomously navigating interactions with humans and tools. Their design and deployment tends to presume they are normal agents capable of sustaining coherent goals, adapting across contexts and acting with a measure of intentionality. These assumptions are critical to prospective use cases in industrial, social and governmental settings. But LMAs are not normal agents. They inherit the structural problems of the large language models (LLMs) around which they are built: hallucinations, jailbreaking, misalignment and unpredictability. In this Position paper we argue LMAs should not be treated as normal agents, because doing so leads to problems that undermine their utility and trustworthiness. We enumerate pathologies of agency intrinsic to LMAs. Despite scaffolding such as external memory and tools, they remain ontologically stateless, stochastic, semantically sensitive, and linguistically intermediated. These pathologies destabilise the ontological properties of LMAs including identifiability, continuity, persistence and and consistency, problematising their claim to agency. In response, we argue LMA ontological properties should be measured before, during and after deployment so that the negative effects of pathologies can be mitigated.