相关论文: Invisible Orchestrators Suppress Protective Behavi…

In this paper, we consider a coordination problem for a class of heterogeneous nonlinear multi-agent systems with a prescribed input-output behavior which was represented by another input-driven system. In contrast to most existing…

Current safety evaluations for LLM-driven agents primarily focus on atomic harms, failing to address sophisticated threats where malicious intent is concealed or diluted within complex tasks. We address this gap with a two-dimensional…

Deploying compound LLM agents in adversarial, partially observable sequential environments requires navigating several design dimensions: (1) what the agent sees, (2) how it reasons, and (3) how tasks are decomposed across components. Yet…

Intraday surgical scheduling is a multi-objective decision problem under uncertainty-balancing elective throughput, urgent and emergency demand, delays, sequence-dependent setups, and overtime. We formulate the problem as a cooperative…

As AI systems advance in capabilities, measuring their safety and alignment to human values is becoming paramount. A fast-growing field of AI research is devoted to developing such assessments. However, most current advances therein may be…

Powerful large language models (LLMs) from different providers have been expensively trained and finetuned to specialize across varying domains. In this work, we introduce a new kind of Conductor model trained with reinforcement learning to…

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

From social networks to traffic routing, artificial learning agents are playing a central role in modern institutions. We must therefore understand how to leverage these systems to foster outcomes and behaviors that align with our own…

Large language models (LLMs) are increasingly deployed in multi-agent systems where agents communicate in natural language to solve tasks jointly. A key capability in such systems is consensus formation, where agents iteratively exchange…

Large Language Models (LLMs) are increasingly used to annotate learning interactions, yet concerns about reliability limit their utility. We test whether verification-oriented orchestration-prompting models to check their own labels…

Recent advances in LLM-based agent systems have shown promise on complex, long-horizon tasks, but existing agent protocols (e.g., A2A and MCP) do not adequately support lifecycle-aware coordination across agents, tools, and environments. To…

The rapid advancement of Large Language Model (LLM)-driven multi-agent systems has significantly streamlined software developing tasks, enabling users with little technical expertise to develop executable applications. While these systems…

LLM-powered Multi-Agent Systems (LLM-MAS) unlock new potentials in distributed reasoning, collaboration, and task generalization but also introduce additional risks due to unguaranteed agreement, cascading uncertainty, and adversarial…

As large language model (LLM) agents evolve from isolated tool users into coordinated teams, reinforcement learning (RL) must optimize not only individual actions but also how work is spawned, delegated, communicated, aggregated, and…

Unpredictable behavior is often taken as evidence of control, yet stochastic dispersion and structured action control need not coincide. This paper tests whether stochastic sampling can substitute for structured mechanisms that couple…

Multi-agent systems are prevalent in a wide range of domains including power systems, vehicular networks, and robotics. Two important problems to solve in these types of systems are how the intentions of non-coordinating agents can be…

LLM-based agents increasingly coordinate decisions in multi-agent systems, often attaching natural-language reasoning to actions. However, reasoning is neither free nor automatically reliable: it incurs computational cost and, without…

We address two major challenges of implicit coordination in multi-agent deep reinforcement learning: non-stationarity and exponential growth of state-action space, by combining Deep-Q Networks for policy learning with Nash equilibrium for…

Enterprise AI deploys dozens of autonomous agent nodes across workflows, each acting on the same entities with no shared memory and no common governance. We identify five structural challenges arising from this memory governance gap: memory…

Autonomous agents based on large language models (LLMs) are rapidly emerging as a general-purpose technology, with recent systems such as OpenClaw extending their capabilities through broad tool use, third-party skills, and deeper…