arXiv AI June 19, 2026 By Gregory Matsnev

Uncertainty Decomposition for Clarification Seeking in LLM Agents

arXiv:2606. 19559v1 Announce Type: new Abstract: Recent position papers argue that the classical aleatoric/epistemic uncertainty framework is insufficient for interactive large language model (LLM) agents and call for underspecification-aware, decomposed, and communicable uncertainty representations that can unlock new agent capabilities such as proactive clarification seeking and shared mental-model building.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 3

Uncertainty-Aware Clarification in LLM Agents with Information Gain

arXiv:2606. 03135v1 Announce Type: new Abstract: Large Language Model (LLM) agents often operate under underspecified user instructions, where latent uncertainty over user intent leads to erroneous tool actions.

By Mengyi Deng, Zhiwei Li, Xin Li, Tingyu Zhu, Ying Zhao, Zhijiang Guo, Wei Wang

llms agents

arXiv AI

Jul 14

AgentAbstain: Do LLM Agents Know When Not to Act?

arXiv:2607. 10059v1 Announce Type: new Abstract: Agent systems based on large language models (LLMs) are increasingly deployed for autonomous tasks, yet existing evaluations mostly focus on task success rather than whether agents know when to abstain.

By Xun Liu, Yi Evie Zhang, Vira Kasprova, Parisa Rabbani, Pardis Sadat Zahraei, Tianyu Zhang, Ali Ebrahimpour-Boroojeny, Varun Chandrasekaran

llms agents benchmarks

arXiv AI

Jul 7

ASK in the Dark: Uncertainty-Gated LLM Assistance under Partial Observability

arXiv:2607. 02686v1 Announce Type: new Abstract: Reinforcement learning agents operating under partial observability must act on incomplete information, making them natural candidates for guidance from small language models (SLMs) that carry broad reasoning priors.

By Juarez Monteiro, Nathan Gavenski, Guilherme Lima, Francisco Galuppo, Odinaldo Rodrigues, Adriano Veloso

llms agents reinforcement-learning

arXiv AI

Jul 15

Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution

arXiv:2607. 13034v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task actually requires.

By Junjie Yin, Xinyu Feng

llms agents benchmarks

arXiv Machine Learning

Jul 30

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents

arXiv:2607. 26865v1 Announce Type: cross Abstract: LLM agents following the ReAct paradigm are promising enablers of complex multi-step tasks, including multi-hop question answering, code generation, and control of physical AI systems.

By Amirmohammad Farzaneh, Osvaldo Simeone

llms agents nlp robotics benchmarks

arXiv AI

1d ago

From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents

arXiv:2608. 16002v1 Announce Type: cross Abstract: Reliable uncertainty quantification (UQ) is essential for deploying large language model (LLM) agents in complex interactive environments.

By Zhengzhao Ma. Boxi Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun

llms agents benchmarks safety

Related stories

Uncertainty-Aware Clarification in LLM Agents with Information Gain

AgentAbstain: Do LLM Agents Know When Not to Act?

ASK in the Dark: Uncertainty-Gated LLM Assistance under Partial Observability

Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents

From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents