Position: Stop Acting Like Language Model Agents Are Normal Agents

2025-02-04 · Elija Perrier, Michael Timothy Bennett

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.

📄 PDF Abstract BibTeX arXiv:2502.10420

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingPosition

HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agents

2026-08-03 · Daeyoung Roh, Donghee Han arxiv

Retrieval-augmented search agents answer multi-hop questions by repeatedly issuing search queries and accumulating evidence. This creates a stopping problem: after the necessary evidence has appeared, further retrieval o…

AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices

2026-05-01 · Dzung Pham, Kleomenis Katevas, Ali Shahin Shamsabadi, Hamed Haddadi arxiv

Autonomous agents powered by large language models (LLMs) are increasingly used to automate complex, multi-step tasks such as coding or web-based question answering. While remote, cloud-based agents offer scalability and…

Question Answering

Position: Deployed Reinforcement Learning should be Continual

2026-06-01 · Parnian Behdin, Kevin Roice, Golnaz Mesbahi arxiv

Reinforcement Learning (RL) has received increasing attention and adoption in real-world use cases. Most of these systems follow a train-then-fix paradigm, where trained agents do not learn while interacting with the wor…

Reinforcement Learning

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

2026-06-27 · Han Luo, Bingbing Wen, Lucy Lu Wang arxiv

LLM agents are expected to act over multiple turns, using search, browsing interfaces, and terminal tools to complete user goals. Yet not every goal is well specified or achievable in the available environment. In such c…

Question Answering

Emergence of Numeric Concepts in Multi-Agent Autonomous Communication

2019-11-04 · Shangmin Guo

With the rapid development of deep learning, most of current state-of-the-art techniques in natural langauge processing are based on deep learning models trained with argescaled static textual corpora. However, we human …

Deep Reinforcement Learning Grounded language learning Reinforcement Learning