Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction and are increasingly being deployed in situations where they might engage with both human and artificial agents. These interactions represent a critical frontier for LLM-based agents, yet existing evaluation methods fail to measure how well these capabilities generalize to novel social situations. In this paper, we introduce a method for evaluating the ability of LLM-based agents to cooperate in zero-shot, mixed-motive environments using Concordia, a natural language multi-agent simulation environment. Our method measures general cooperative intelligence by testing an agent's ability to identify and exploit opportunities for mutual gain across diverse partners and contexts. We present empirical results from the NeurIPS 2024 Concordia Contest, where agents were evaluated on their ability to achieve mutual gains across a suite of diverse scenarios ranging from negotiation to collective action problems. Our findings reveal significant gaps between current agent capabilities and the robust generalization required for reliable cooperation, particularly in scenarios demanding persuasion and norm enforcement.

Effective human-AI coordination requires artificial agents capable of exhibiting and responding to human-like behaviors while adapting to changing contexts. Imitation learning has emerged as one of the prominent approaches to build such agents by training them to mimic human-demonstrated behaviors. However, current methods struggle to capture the inherent diversity and non-Markovian nature of human behavior and lack the ability to steer behavior at inference time. Drawing inspiration from the theory of human cognitive processes, where inner speech guides action selection before execution, we propose MIMIC (Modeling Inner Motivations for Imitation and Control), a framework that uses language as an internal representation of behavioral intent. MIMIC employs the novel use of vision-language models as linguistic scaffolding to train a conditional variational autoencoder capable of generating inner speech from observations. A diffusion-based behavior cloning policy then selects actions conditioned on current observations and the generated inner speech. MIMIC enables fine-grained steering of behavior at inference time by conditioning the agent on behavior-specific speech. Experiments across robotic manipulation tasks and human-AI collaboration games demonstrate that MIMIC significantly enhances both behavior diversity and fidelity to human demonstrations while enabling nuanced behavioral steering without training on additional demonstrations.

Diffusion models lend transformative capabilities to the graph generation task, yet controlling the properties of the generated graphs remains challenging. Recent approaches augment support for controlling soft, differentiable properties but they fail to handle user-specified hard constraints that are non-differentiable. This often results in vague control, unsuitable for applications like drug discovery that demand satisfaction of precise constraints, e.g., the maximum number of bonds. To address this, we formalize the problem of controlled graph generation and introduce PRODIGY (PROjected DIffusion for controlled Graph Generation), an innovative plug-and-play approach enabling the generation of graphs with precise control, from any pre-trained diffusion model. PRODIGY employs a novel operator to project the samples at each diffusion step onto the specified constrained space. For a large class of practical constraints and a variety of graphs, our extensive experiments demonstrate that PRODIGY empowers state-of-the-art continuous and discrete diffusion models to produce graphs meeting specific, hard constraints. Our approach achieves up to 100% constraint satisfaction for non-attributed and molecular graphs, under a variety of constraints, marking a significant step forward in precise, interpretable graph generation. Code is provided on the project webpage: https://prodigy-diffusion.github.io/.

Multi-agent AI research promises a path to develop human-like and human-compatible intelligent technologies that complement the solipsistic view of other approaches, which mostly do not consider interactions between agents. Aiming to make progress in this direction, the Melting Pot contest 2023 focused on the problem of cooperation among interacting agents and challenged researchers to push the boundaries of multi-agent reinforcement learning (MARL) for mixed-motive games. The contest leveraged the Melting Pot environment suite to rigorously evaluate how well agents can adapt their cooperative skills to interact with novel partners in unforeseen situations. Unlike other reinforcement learning challenges, this challenge focused on social rather than environmental generalization. In particular, a population of agents performs well in Melting Pot when its component individuals are adept at finding ways to cooperate both with others in their population and with strangers. Thus Melting Pot measures cooperative intelligence.The contest attracted over 600 participants across 100+ teams globally and was a success on multiple fronts: (i) it contributed to our goal of pushing the frontiers of MARL towards building more cooperatively intelligent agents, evidenced by several submissions that outperformed established baselines; (ii) it attracted a diverse range of participants, from independent researchers to industry affiliates and academic labs, both with strong background and new interest in the area alike, broadening the field’s demographic and intellectual diversity; and (iii) analyzing the submitted agents provided important insights, highlighting areas for improvement in evaluating agents' cooperative intelligence. This paper summarizes the design aspects and results of the contest and explores the potential of Melting Pot as a benchmark for studying Cooperative AI. We further analyze the top solutions and conclude with a discussion on promising directions for future research.

Real-world graphs such as social networks, communication networks, and rating networks are constantly evolving over time. Many deep learning architectures have been developed to learn effective node representations using both graph structure and dynamics. While being crucial for practical applications, the robustness of these representation learners for dynamic graphs in the presence of adversarial attacks is highly understudied. In this work, we design a novel adversarial attack on discrete-time dynamic graph models where we desire to perturb the input graph sequence in a manner that preserves the temporal dynamics of the graph while dropping the performance of representation learners. To this end, we motivate a novel Temporal Dynamics-Aware Perturbation (TDAP) constraint, which ensures that perturbations introduced at each time step are restricted to only a small fraction of the number of changes in the graph since the previous time step. We present a theoretically-motivated Projected Gradient Descent approach for dynamic graphs to find effective perturbations under the TDAP constraint. Experiments on two tasks - dynamic link prediction and node classification, show that our approach is up to 4x more effective than the baseline methods for attacking these models. We extend our approach to a more practical online setting where graphs become available in real-time and show up to 5x superior performance over baselines We also show that our approach successfully evades state-of-the-art neural approaches for anomaly detection, thereby promoting the need to study robustness as a part of representation-learning approaches for dynamic graphs.

Formation mechanisms are fundamental to the study of complex networks, but learning them from observations is challenging. In real-world domains, one often has access only to the final constructed graph, instead of the full construction process, and observed graphs exhibit complex structural properties. In this work, we propose GraphOpt, an end-to-end framework that jointly learns an implicit model of graph structure formation and discovers an underlying optimization mechanism in the form of a latent objective function. The learned objective can serve as an explanation for the observed graph properties, thereby lending itself to transfer across different graphs within a domain. GraphOpt poses link formation in graphs as a sequential decision-making process and solves it using maximum entropy inverse reinforcement learning algorithm. Further, it employs a novel continuous latent action space that aids scalability. Empirically, we demonstrate that GraphOpt discovers a latent objective transferable across graphs with different characteristics. GraphOpt also learns a robust stochastic policy that achieves competitive link prediction performance without being explicitly trained on this task and further enables construction of graphs with properties similar to those of the observed graph.

Real-world networks, especially the ones that emerge due to actions of animate agents (e.g. humans, animals), are the result of underlying strategic mechanisms aimed at maximizing individual or collective benefits. Learning approaches built to capture these strategic insights would gain interpretability and flexibility benefits that are required to generalize beyond observations. To this end, we consider a game-theoretic formalism of network emergence that accounts for the underlying strategic mechanisms and take it to the observed data. We propose MINE (Multi-agent Inverse models of Network Emergence mechanism), a new learning framework that solves Markov-Perfect network emergence games using multi-agent inverse reinforcement learning. MINE jointly discovers agents' strategy profiles in the form of network emergence policy and the latent payoff mechanism in the form of learned reward function. In the experiments, we demonstrate that MINE learns versatile payoff mechanisms that: highly correlates with the ground truth for a synthetic case; can be used to analyze the observed network structure; and enable effective transfer in specific settings. Further, we show that the network emergence game as a learned model supports meaningful strategic predictions, thereby signifying its applicability to a variety of network analysis tasks.

Rakshit Trivedi, Bunyamin Sisman, Xin Luna Dong, Christos Faloutsos, Jun Ma, Hongyuan Zha. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018.

We propose the first multistage intervention framework that tackles fake news in social networks by combining reinforcement learning with a point process network activity model. The spread of fake news and mitigation events within the network is modeled by a multivariate Hawkes process with additional exogenous control terms. By choosing a feature representation of states, defining mitigation actions and constructing reward functions to measure the effectiveness of mitigation activities, we map the problem of fake news mitigation into the reinforcement learning framework. We develop a policy iteration method unique to the multivariate networked point process, with the goal of optimizing the actions for maximal reward under budget constraints. Our method shows promising performance in real-time intervention experiments on a Twitter network to mitigate a surrogate fake news campaign, and outperforms alternatives on synthetic datasets.

The availability of large scale event data with time stamps has given rise to dynamically evolving knowledge graphs that contain temporal information for each edge. Reasoning over time in such dynamic knowledge graphs is not yet well understood. To this end, we present Know-Evolve, a novel deep evolutionary knowledge network that learns non-linearly evolving entity representations over time. The occurrence of a fact (edge) is modeled as a multivariate point process whose intensity function is modulated by the score for that fact computed based on the learned entity embeddings. We demonstrate significantly improved performance over various relational learning approaches on two large scale real-world datasets. Further, our method effectively predicts occurrence or recurrence time of a fact which is novel compared to prior reasoning approaches in multi-relational setting.

Large volumes of event data are becoming increasingly available in a wide variety of applications, such as healthcare analytics, smart cities and social network analysis. The precise time interval or the exact distance between two events carries a great deal of information about the dynamics of the underlying systems. These characteristics make such data fundamentally different from independently and identically distributed data and time-series data where time and space are treated as indexes rather than random variables. Marked temporal point processes are the mathematical framework for modeling event data with covariates. However, typical point process models often make strong assumptions about the generative processes of the event data, which may or may not reflect the reality, and the specifically fixed parametric assumptions also have restricted the expressive power of the respective processes. Can we obtain a more expressive model of marked temporal point processes? How can we learn such a model from massive data?

Matching users to the right items at the right time is a fundamental task in recommendation systems. As users interact with different items over time, users' and items' feature may evolve and co-evolve over time. Traditional models based on static latent features or discretizing time into epochs can become ineffective for capturing the fine-grained temporal dynamics in the user-item interactions. We propose a coevolutionary latent feature process model that accurately captures the coevolving nature of users' and items' feature. To learn parameters, we design an efficient convex optimization algorithm with a novel low rank space sharing constraints. Extensive experiments on diverse real-world datasets demonstrate significant improvements in user behavior prediction compared to state-of-the-arts.