Related papers: Governance by Construction for Generalist Agents
Generative agents, which implement behaviors using a large language model (LLM) to interpret and evaluate an environment, has demonstrated the capacity to solve complex tasks across many social and technological domains. However, when these…
Authorizing Large Language Model (LLM)-driven agents to dynamically invoke tools and access protected resources introduces significant security risks, and the risks grow dramatically as agents engage in multi-turn conversations and scale…
LLM agents are increasingly used for code generation, but physics-based simulation poses a deeper challenge: natural-language descriptions of simulation models are inherently underspecified, and different admissible resolutions of implicit…
With the rise of large language models (LLMs), LLM agents capable of autonomous reasoning, planning, and executing complex tasks have become a frontier in artificial intelligence. However, how to translate the research on general agents…
Policymakers must often act under conditions of deep uncertainty, such as emergency response, where predicting the specific impacts of a policy apriori is implausible. Large Language Model (LLM) agent simulations have been proposed as tools…
The rapid advancement of large language model (LLM) agents has raised new concerns regarding their safety and security. In this paper, we propose GuardAgent, the first guardrail agent to protect target agents by dynamically checking whether…
We study the problem of learning a good set of policies, so that when combined together, they can solve a wide variety of unseen reinforcement learning tasks with no or very little new data. Specifically, we consider the framework of…
High-stakes decision systems increasingly require structured justification, traceability, and auditability to ensure accountability and regulatory compliance. Formal arguments commonly used in the certification of safety-critical systems…
LLM-based agentic systems are rapidly evolving to perform complex autonomous tasks through dynamic tool invocation, stateful memory management, and multi-agent collaboration. However, this semantics-driven execution paradigm creates a…
Coding agents are rapidly changing the landscape of software development, moving from inline completion to autonomous systems that edit repositories, open pull requests, respond to issues, and run scheduled or webhook triggered routines…
What does it mean to plan? Current agentic systems, whether scaffolded workflows or end-to-end policies, rely on reactive decision-making: selecting the next action via a fixed procedure with at most undifferentiated adaptive computation…
Large language models increasingly operate as autonomous agents that select and invoke tools from large registries. We identify a critical gap: when unauthorized tools are visible in an agent's context, models select them in adversarial…
We explore the use of GPT-4 on a humanoid robot in simulation and the real world as proof of concept of a novel large language model (LLM) driven behaviour method. LLMs have shown the ability to perform various tasks, including robotic…
We present five results in the theory of structural governance for cognitive workflow systems. Three are mechanized in Coq 8.19 using the Interaction Trees library with parameterized coinduction; two are proved on paper with explicit…
We introduce a novel learning and planning framework that replaces traditional reward-based optimisation with constructive logical inference. In our model, actions, transitions, and goals are represented as logical propositions, and…
Tool learning empowers large language models (LLMs) as agents to use external tools and extend their utility. Existing methods employ one single LLM-based agent to iteratively select and execute tools, thereafter incorporating execution…
A policy-governed RAG architecture is specified for audit-ready generation in regulated workflows, organized as a triptych: (I) Contracts/Control (SHRDLU-like), which governs output adherence to legal and internal policies; (II)…
Letting robots emulate human behavior has always posed a challenge, particularly in scenarios involving multiple robots. In this paper, we presented a framework aimed at achieving multi-agent reinforcement learning for robot control in…
This study presents the LLM-Agent-Controller, a multi-agent large language model (LLM) system developed to address a wide range of problems in control engineering (Control Theory). The system integrates a central controller agent with…
Workforce transformations are difficult to forecast and costly to mismanage. In particular, the integration of artificial intelligence into knowledge work currently affects a substantial share of the global workforce, yet this transition…