paper-with-me

홈 › Papers

Leverage Laws: A Per-Task Framework for Human-Agent Collaboration

2026-04-27 · Stan Loosmore arxiv

We propose a per-task leverage ratio for human-agent collaboration: human work displaced by an agent, divided by the human time required to specify the task, resolve mid-run interrupts, and review the result. The denominator decomposes into three channels through which a conserved per-task information requirement must flow, each with its own time-cost scalar. We show that information density itself is directional and bounded by separate ceilings on human-to-agent and agent-to-human flow, and that the asymptotic behavior of leverage decomposes into two scaling axes (capability and memory) with a non-zero floor on the planning term set by irreducible task novelty bounded by human throughput. We extend this per-task analysis to a windowed leverage measure that accommodates recurring tasks, spawned subtasks, and amortized system-design investment. The per-task ceiling does not bind the windowed measure, though both remain bounded: $L_{\text{task}}$ by per-task novelty, $L_{\text{window}}$ by the stock of accumulated planning investment that pays out within the window. The framework operationalizes aspects of earlier qualitative work on supervisory control (Sheridan, 1992), common ground (Clark & Brennan, 1991), and mixed-initiative interaction (Horvitz, 1999) within a single normative ratio, and produces a list of testable empirical questions that we leave as open problems.

📄 PDF Abstract BibTeX arXiv:2604.25040

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Identifying Reasoning Flaws in Planning-Based RL Using Tree Explanations

2021-09-28 · Kin-Ho Lam, Zhengxian Lin, Jed Irvine, Jonathan Dodge 외

Enabling humans to identify potential flaws in an agent's decision making is an important Explainable AI application. We consider identifying such flaws in a planning-based deep reinforcement learning (RL) agent for a co…

Decision MakingDeep Reinforcement LearningReinforcement Learning (RL)

Can Language Models Discover Scaling Laws?

2025-07-27 · Haowei Lin, Haotian Ye, Wenzheng Feng, Quzhe Huang 외 arxiv

Discovering scaling laws for predicting model performance at scale is a fundamental and open-ended challenge, mostly reliant on slow, case specific human experimentation. To investigate the potential for LLMs to automate…

LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior

2026-06-26 · Qinhong Zhou, Chuang Gan, Anoop Cherian arxiv

Embodied agents operating in decentralized and partially observable environments have attracted growing attention in recent years. However, existing large language model (LLM)-based agents often exhibit behaviors that ar…

Legible Normativity for AI Alignment: The Value of Silly Rules

2018-11-03 · Dylan Hadfield-Menell, McKane Andrus, Gillian K. Hadfield

It has become commonplace to assert that autonomous agents will have to be built to follow human rules of behavior--social norms and laws. But human laws and norms are complex and culturally varied systems, in many cases…

An alignment safety case sketch based on debate

2025-05-06 · Marie Davidsen Buhl, Jacob Pfau, Benjamin Hilton, Geoffrey Irving

If AI systems match or exceed human capabilities on a wide range of tasks, it may become difficult for humans to efficiently judge their actions -- making it hard to use human feedback to steer them towards desirable tra…