21 accepted papers
Theory of Mind (ToM) refers to the ability to reason about others’ mental states, and higher-order ToM involves considering that others also possess their own ToM. Equipping large language model (LLM)-driven agents with ToM has long been considered to improve their coordination in multiagent collabo
Large Language Models (LLMs) have rapidly advanced, with Gemini-3-Pro setting a new performance milestone. In this work, we explore collective intelligence as an alternative to monolithic scaling, and demonstrate that open-source LLMs' collaboration can surpass Gemini-3-Pro. We first revisit LLM rou…
The growing capabilities of large language models (LLMs) have driven their widespread deployment across diverse domains, even in potentially high-risk scenarios. Despite advances in safety alignment techniques, current models remain vulnerable to emerging *persona-based jailbreak attacks*. Existing …
This paper presents a simple, effective, and cost-efficient strategy, named ModelSwitch, to improve LLM performance by scaling test-time compute. ModelSwitch builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple models, even weaker ones, to leverage the
Large language models (LLMs) often exhibit complementary strengths. Model routing harnesses these strengths by dynamically directing each query to the most suitable model, given a candidate model pool. However, routing performance relies on accurate model representations, and adding new models typic
Reinforcement Learning (RL) has demonstrated its potential to improve the reasoning ability of Large Language Models (LLMs), yet most existing Reinforcement Finetuning (RFT) methods are inherently \textit{on-policy} RL, failing to reuse historical data and thus preventing efficient scaling. In this…
Proprietary models are increasingly dominating the race for ever-larger language models. Can open-source, smaller models remain competitive across a broad range of tasks? In this paper, we present the Avengers---a lightweight framework that leverages the collective intelligence of these smaller mod
Despite the growing popularity of graph attention mechanisms, their theoretical understanding remains limited. This paper aims to explore the conditions under which these mechanisms are effective in node classification tasks through the lens of Contextual Stochastic Block Models (CSBMs). Our theoret…
Recent research on Reasoning of Large Language Models (LLMs) has sought to further enhance their performance by integrating meta-thinking—enabling models to monitor, evaluate, and control their reasoning processes for more adaptive and effective problem-solving. However, current single-agent work la…
Large Language Models (LLMs) require alignment via reinforcement learning (RL) to effectively perform task-specific objectives, such as human preference alignment and enhanced reasoning. While Proximal Policy Optimization (PPO) is widely adopted, its computational overhead, stemming from additional
Large Language Models (LLMs) have achieved remarkable progress on advanced reasoning tasks such as mathematics and coding competitions. Meanwhile, physics, despite being both reasoning-intensive and essential to real-world understanding, received limited academic and industrial attention. This paper…
Iterated prisoner’s dilemma (IPD) and its variants are fundamental models for understanding the evolution of cooperation in human society as well as AI systems. In this paper, we focus on multichannel IPD, and examine how an agent should behave to obtain generally high payoffs under this setting.…
Decision-making problems, categorized as single-agent, e.g., Atari, cooperative multi-agent, e.g., Hanabi, competitive multi-agent, e.g., Hold'em poker, and mixed cooperative and competitive, e.g., football, are ubiquitous in the real world. Although various methods have been proposed to address the…
Social norms play a crucial role in guiding agents towards understanding and adhering to standards of behavior, thus reducing social conflicts within multi-agent systems (MASs). However, current LLM-based (or generative) MASs lack the capability to be normative. In this paper, we propose a novel arc…
Developing a dynamical model for learning in games has attracted much recent interest. In stochastic games, agents need to make decisions in multiple states, and transitions between states, in turn, influence the dynamics of strategies. While previous works typically focus either on 2-agent stochast…
Altruistic punishment (or punishment) has been extensively shown as an important mechanism for promoting cooperation in human societies. In AI, the emergence of punishment has received much recent interest. In this paper, we contribute with a novel evolutionary game theoretic model to study the impa…
Reaching consensus and convergence to equilibrium are two major challenges of multi-agent systems. Although each has attracted significant attention, relatively few studies address both challenges at the same time. This paper examines the connection between the notions of consensus and equilibrium i…
Modeling the dynamics of multi-agent learning has long been an important research topic. The focus of previous research has been either on 2-agent settings or well-mixed infinitely large agent populations. In this paper, we consider the scenario where n Q-learning agents locate on regular graphs, su…
The theoretical underpinnings of multiagent reinforcement learning has recently attracted much attention. In this work, we focus on the generalized social learning (GSL) protocol --- an agent interaction protocol that is widely adopted in the literature, and aim to develop an accurate theoretical m…
Understanding the learning dynamics in multiagent systems is an important and challenging task. Past research on multi-agent learning mostly focuses on two-agent settings. In this paper, we consider the scenario in which a population of infinitely many agents apply regret minimization in repeated sy…
Modelling the dynamics of multi-agent learning has long been an important research topic, but all of the previous works focus on 2-agent settings and mostly use evolutionary game theoretic approaches. In this paper, we study an n-agent setting with n tends to infinity, such that agents learn their p…