相关论文: From Helpfulness to Toxic Proactivity: Diagnosing …

Most LLM benchmarks score how well a model responds to explicit requests. They leave unmeasured a different conversational ability: noticing and acting on needs the user has implied but not said. We call this \emph{conversational…

The ability to coordinate actions across multiple agents is critical for solving complex, real-world problems. Large Language Models (LLMs) have shown strong capabilities in communication, planning, and reasoning, raising the question of…

Recent advances in large language models (LLMs) have facilitated the widespread deployment of LLMs as interactive agents capable of reasoning, planning, and tool use. Despite strong performance on existing benchmarks, such agents often…

With the continuous development of large language models (LLMs), transformer-based models have made groundbreaking advances in numerous natural language processing (NLP) tasks, leading to the emergence of a series of agents that use LLMs as…

Large language models (LLMs) have empowered nodes within multi-agent networks with intelligence, showing growing applications in both academia and industry. However, how to prevent these networks from generating malicious information…

As LLM-based agents increasingly operate in multi-agent systems, understanding adversarial manipulation becomes critical for defensive design. We present a systematic study of intentional deception as an engineered capability, using…

Advanced reasoning models with agentic capabilities (AI agents) are deployed to interact with humans and to solve sequential decision-making problems under (approximate) utility functions and internal models. When such problems have…

Agentic AI shifts LLM serving from isolated prompt-generation requests to stateful, multi-turn executions that repeatedly invoke the model, call tools, and grow context over time. This paper characterizes ReAct-style agents from both the…

Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world educational environments, significantly boosting assessment efficiency and scalability. However, when these…

Large language model (LLM) agents with tool-calling capabilities are increasingly deployed in production systems, yet a fundamental reliability question remains under-explored: does the same agent behave the same way twice? We present a…

Large Language Model (LLM)-based multi-agent systems are increasingly applied to automate computational workflows in science and engineering. However, how inter-agent dynamics influence reasoning quality and verification reliability remains…

Effective collaboration begins with knowing when to ask for help. For example, when trying to identify an occluded object, a human would ask someone to remove the obstruction. Can MLLMs exhibit a similar "proactive" behavior by requesting…

This paper presents a comparative analysis of cooperative resilience in multi-agent systems, defined as the ability to anticipate, resist, recover from, and transform to disruptive events that affect collective well-being. We focus on…

It is increasingly important that LLM agents interact effectively and safely with other goal-pursuing agents, yet, recent works report the opposite trend: LLMs with stronger reasoning capabilities behave _less_ cooperatively in mixed-motive…

Large language models (LLMs) have demonstrated impressive capabilities as autonomous agents with rapidly expanding applications in various domains. As these agents increasingly engage in socioeconomic interactions, identifying their…

Large language models (LLMs) gained immense popularity due to their impressive capabilities in unstructured conversations. Empowering LLMs with advanced prompting strategies such as reasoning and acting (ReAct) (Yao et al., 2022) has shown…

Self-modification of agents embedded in complex environments is hard to avoid, whether it happens via direct means (e.g. own code modification) or indirectly (e.g. influencing the operator, exploiting bugs or the environment). It has been…

We present an effective technique for training deep learning agents capable of negotiating on a set of clauses in a contract agreement using a simple communication protocol. We use Multi Agent Reinforcement Learning to train both agents…

Agent faults pose a significant threat to the performance of multi-agent reinforcement learning (MARL) algorithms, introducing two key challenges. First, agents often struggle to extract critical information from the chaotic state space…

While passive agents merely follow instructions, proactive agents align with higher-level objectives, such as assistance and safety by continuously monitoring the environment to determine when and how to act. However, developing proactive…