The paper introduces the concept of "empty commitments," promises made by AI agents that cannot be fulfilled due to the absence of necessary tools or runtime capabilities. It defines three failure types, proposes a detection checker, and evaluates it on 400 human-labeled examples and a benchmark of 293 follow‑up requests. The study shows that many open‑weight models frequently issue such empty commitments, and that simple interventions—informing the model of its runtime, adding a capability card, or running a checker loop—can significantly reduce these failures.
By Jiaqi Tang, Bingyu Shen, Lan Wei, Qing Lu, Bethel Ololade, Danny Galvis, Miles Q. Li, Bin Hu, Boyang Li
arXiv:2605. 08747v4 Announce Type: replace Abstract: Standard embodied evaluations do not independently score whether an agent correctly commits to task completion at episode closure, a capacity we call terminal commitment.
By Ying Chen, Lihuang Fang, Rui Jiang, Mingxu Wang, Zhifeng Gu, Lei Yi, Jie Chen
arXiv:2606. 08552v1 Announce Type: new Abstract: I discuss some quantitative representations of Promise Theory for processes involving autonomous agents.
By Mark Burgess
arXiv:2608. 09939v1 Announce Type: cross Abstract: Production teams deploying LLM chat agents face a specific quality assurance gap: existing evaluation tools test individual responses or simulate social interactions, but none systematically verify whether real users can achieve their goals through multi-turn conversation.
By Alexandre Cristov\~ao Maiorano
arXiv:2609.13800v1 Announce Type: new
Abstract: Routing and cascades reduce tool-agent cost by transferring control across models, but stateful handoffs must preserve accepted choices, realized effec...
By Runzhi Deng, Yiming Zhong, Fang Zhao, Pan Zhou
arXiv:2601.13206v2 Announce Type: replace
Abstract: Large Language Models (LLMs) generate text token-by-token in discrete time, yet real-world communication, from therapy sessions to business negotia...
By Neil K. R. Sehgal, Sharath Chandra Guntuku, Lyle Ungar
arXiv:2607. 14553v1 Announce Type: new Abstract: Modern industrial environments increasingly run many autonomous subsystems at once - schedulers, energy managers, vehicle fleets - each pursuing its own goals while sharing the same physical resources.
By Artan Markaj, Raphael H\"ofer, Felix Gehlhoff
arXiv:2608.22055v3 Announce Type: replace
Abstract: Embodied language-model agents must coordinate interdependent actions while each holds private task information. In dialogue-based coordination, mo...
By Junning Zhu, Peng He, Haohan Yuan, Jianpeng Liang
arXiv:2609.37453v1 Announce Type: new
Abstract: When a user changes their mind partway through a task, an agent that has already split the task into sub-goals and paid for tool calls must decide, per...
By Spandan Ghose Chowdhury
arXiv:2607. 24167v1 Announce Type: new Abstract: Long-horizon web agents often go off track before final failure: a trajectory can remain locally plausible even after the current state, reused skill, or plan assumption no longer supports the user instruction.
By Guangyi Liu, Huan Zhao, Quanming Yao
The paper proposes five runtime primitives—discovery, identity, governance, attestation, and supply chain—to manage autonomous AI agents in enterprise settings. It argues that traditional control models fail because agents are transient, model-driven, and self‑discoverable, making runtime governance essential. The authors detail an implementation that mediates agent actions against policy, authorizes them via a per‑tenant vocabulary, and records them in a verifiable ledger, noting the associated operational costs and partial deployment status.
By Jiten Oswal, John Cadeddu
The paper introduces PlanFence, a dependency-scoped action‑validation protocol for distributed large language model (LLM) agent teams. PlanFence requires plans to cite the exact public records they rely on, and executors validate only those records that could affect the pending action, replanning or blocking if validation is incomplete. In 30 controlled live workflows, a freshness‑only executor always acted on obsolete plans, whereas PlanFence completed all tasks without invalid actions, demonstrating controlled safety and system‑cost benefits.
By Evan Chen, Shiqiang Wang, Christopher G. Brinton