The improvement of economic policymaking presents an opportunity for broad societal benefit, a notion that has inspired research towards AI-driven policymaking tools. AI policymaking holds the potential to surpass human performance through the ability to process data quickly at scale. However, existing RL-based methods exhibit sample inefficiency, and are further limited by an inability to flexibly incorporate nuanced information into their decision-making processes. Thus, we propose a novel method in which we instead utilize pre-trained Large Language Models (LLMs), as sample-efficient policymakers in socially complex multi-agent reinforcement learning (MARL) scenarios. We demonstrate significant efficiency gains, outperforming existing methods across three environments. Our code is available at https://github.com/hegasz/large-legislative-models.

We present Agent S, an open agentic framework that enables autonomous interaction with computers through a Graphical User Interface (GUI), aimed at transforming human-computer interaction by automating complex, multi-step tasks. Agent S aims to address three key challenges in automating computer tasks: acquiring domain-specific knowledge, planning over long task horizons, and handling dynamic, non-uniform interfaces. To this end, Agent S introduces experience-augmented hierarchical planning, which learns from external knowledge search and internal experience retrieval at multiple levels, facilitating efficient task planning and subtask execution. In addition, it employs an Agent-Computer Interface (ACI) to better elicit the reasoning and control capabilities of GUI agents based on Multimodal Large Language Models (MLLMs). Evaluation on the OSWorld benchmark shows that Agent S outperforms the baseline by 9.37% on success rate (an 83.6% relative improvement) and achieves a new state-of-the-art. Comprehensive analysis highlights the effectiveness of individual components and provides insights for future improvements. Furthermore, Agent S demonstrates broad generalizability to different operating systems on a newly-released WindowsAgentArena benchmark. Code available at https://github.com/simular-ai/Agent-S.

Large language models (LLMs) have achieved reasonable quality improvements in machine translation (MT). However, most current research on MT-LLMs still faces significant challenges in maintaining translation consistency and accuracy when processing entire documents. In this paper, we introduce DelTA, a Document-levEL Translation Agent designed to overcome these limitations. DelTA features a multi-level memory structure that stores information across various granularities and spans, including Proper Noun Records, Bilingual Summary, Long-Term Memory, and Short-Term Memory, which are continuously retrieved and updated by auxiliary LLM-based components. Experimental results indicate that DelTA significantly outperforms strong baselines in terms of translation consistency and quality across four open/closed-source LLMs and two representative document translation datasets, achieving an increase in consistency scores by up to 4.58 percentage points and in COMET scores by up to 3.16 points on average. DelTA employs a sentence-by-sentence translation strategy, ensuring no sentence omissions and offering a memory-efficient solution compared to the mainstream method. Furthermore, DelTA improves pronoun translation accuracy, and the summary component of the agent also shows promise as a tool for query-based summarization tasks. We release our code and data at https://github.com/YutongWang1216/DocMTAgent.

Large Language Model (LLM) based multi-agent systems (MAS) show remarkable potential in collaborative problem-solving, yet they still face critical challenges: low communication efficiency, poor scalability, and a lack of effective parameter-updating optimization methods. We present Optima, a novel framework that addresses these issues by significantly enhancing both communication efficiency and task effectiveness in LLM-based MAS through LLM training. Optima employs an iterative generate, rank, select, and train paradigm with a reward function balancing task performance, token efficiency, and communication readability. We explore various RL algorithms, including Supervised Fine-Tuning, Direct Preference Optimization, and their hybrid approaches, providing insights into their effectiveness-efficiency trade-offs. We integrate Monte Carlo Tree Search-inspired techniques for DPO data generation, treating conversation turns as tree nodes to explore diverse interaction paths. Evaluated on common multi-agent tasks, including information-asymmetric question answering and complex reasoning, Optima shows consistent and substantial improvements over single-agent baselines and vanilla MAS based on Llama 3 8B, achieving up to 2.8x performance gain with less than 10\% tokens on tasks requiring heavy information exchange. Moreover, Optima's efficiency gains open new possibilities for leveraging inference-compute more effectively, leading to improved inference-time scaling laws. By addressing fundamental challenges in LLM-based MAS, Optima shows the potential towards scalable, efficient, and effective MAS (https://chenweize1998.github.io/optima-project-page).

Residential rooftop solar adoption is considered crucial for reducing carbon emissions. The lack of photovoltaic (PV) data at a finer resolution (e.g., household, hourly levels) poses a significant roadblock to informed decision-making. We discuss a novel methodology to generate a highly granular, residential-scale realistic dataset for rooftop solar adoption across the contiguous United States. The data-driven methodology consists of: (i) integrated machine learning models to identify PV adopters, (ii) methods to augment the data using explainable AI techniques to glean insights about key features and their interactions, and (iii) methods to generate household-level hourly solar energy output using an analytical model. The resulting synthetic datasets are validated using real-world data and can serve as a digital twin for modeling downstream tasks. Finally, a policy-based case study utilizing the digital twin for Virginia demonstrated increased rooftop solar adoption with the 30\% Federal Solar Investment Tax Credit, especially in Low-to-Moderate-Income communities.

Agent-based models have proven to be useful tools in supporting decision-making processes in different application domains. The advent of modern computers and supercomputers has enabled these bottom-up approaches to realistically model human mobility and contact behavior. The COVID-19 pandemic showcased the urgent need for detailed and informative models that can answer research questions on transmission dynamics. We present a sophisticated agent-based model to simulate the spread of respiratory diseases. The model is highly modularized and can be used on various scales, from a small collection of buildings up to cities or countries. Although not being the focus of this paper, the model has undergone performance engineering on a single core and provides an efficient intra- and inter-simulation parallelization for time-critical decision-making processes. In order to allow answering research questions on individual level resolution, nonpharmaceutical intervention strategies such as face masks or venue closures can be implemented for particular locations or agents. In particular, we allow for sophisticated testing and isolation strategies to study the effects of minimal-invasive infectious disease mitigation. With realistic human mobility patterns for the region of Brunswick, Germany, we study the effects of different interventions between March 1st and May 30, 2021 in the SARS-CoV-2 pandemic. Our analyses suggest that symptom-independent testing has limited impact on the mitigation of disease dynamics if the dark figure in symptomatic cases is high. Furthermore, we found that quarantine length is more important than quarantine efficiency but that, with sufficient symptomatic control, also short quarantines can have a substantial effect.

We propose a new variant of the strategic classification problem: a principal reveals a classifier, and $n$ agents report their (possibly manipulated) features to be classified. Motivated by real-world applications, our model crucially allows the manipulation of one agent to affect another; that is, it explicitly captures inter-agent externalities. The principal-agent interactions are formally modeled as a Stackelberg game, with the resulting agent manipulation dynamics captured as a simultaneous game. We show that under certain assumptions, the pure Nash Equilibrium of this agent manipulation game is unique and can be efficiently computed. Leveraging this result, PAC learning guarantees are established for the learner: informally, we show that it is possible to learn classifiers that minimize loss on the distribution, even when a random number of agents are manipulating their way to a pure Nash Equilibrium. We also comment on the optimization of such classifiers through gradient-based approaches. This work sets the theoretical foundations for a more realistic analysis of classifiers that are robust against multiple strategic actors interacting in a common environment.

Among sub-optimal Multi-Agent Path Finding (MAPF) solvers, rule-based algorithms are particularly appealing since they are complete. Even in crowded scenarios, they allow finding a feasible solution that brings each agent to its target, preventing deadlock situations. However, generally, rule-based algorithms provide much longer solutions than the shortest one. The main contribution of this paper is introducing a new local search procedure for improving a known feasible solution. We start from a feasible sub-optimal solution, and perform a local search in a neighborhood of this solution. If we are able to find a shorter solution, we repeat this procedure until the solution cannot be shortened anymore. At the end, we obtain a solution that is still sub-optimal, but generally of much better quality than the initial one. We propose two different local search policies. In the first, we explore all paths in which the agents positions remain in a neighborhood of the corresponding positions of the reference solution. In the second, we set an upper limit to the number of agents that can change their path with respect to the reference solution. These two different policies can also be alternated. We explore the neighborhoods by dynamic programming. The fact that our search is local is fundamental in terms of time complexity. Indeed, if the dynamic programming approach is applied to the full MAPF problem, the number of explored states grows exponentially with the number of agents. Instead, the introduction of a locality constraint allows exploring the neghborhoods in a time that grows polynomially with respect to the number of agents.

As large language models (LLMs) are rapidly advancing and achieving near-human capabilities, aligning them with human values is becoming more urgent. In scenarios where LLMs outperform humans, we face a weak-to-strong alignment problem where we need to effectively align strong student LLMs through weak supervision generated by weak teachers. Existing alignment methods mainly focus on strong-to-weak alignment and self-alignment settings, and it is impractical to adapt them to the much harder weak-to-strong alignment setting. To fill this gap, we propose a multi-agent contrastive preference optimization (MACPO) framework. MACPO facilitates weak teachers and strong students to learn from each other by iteratively reinforcing unfamiliar positive behaviors while penalizing familiar negative ones. To get this, we devise a mutual positive behavior augmentation strategy to encourage weak teachers and strong students to learn from each other's positive behavior and further provide higher quality positive behavior for the next iteration. Additionally, we propose a hard negative behavior construction strategy to induce weak teachers and strong students to generate familiar negative behavior by fine-tuning on negative behavioral data. Experimental results on the HH-RLHF and PKU-SafeRLHF datasets, evaluated using both automatic metrics and human judgments, demonstrate that MACPO simultaneously improves the alignment performance of strong students and weak teachers. Moreover, as the number of weak teachers increases, MACPO achieves better weak-to-strong alignment performance through more iteration optimization rounds.

Recent advances in the fields of natural language processing and computer vision have shown great potential in understanding the underlying dynamics of the world from large-scale internet data. However, translating this knowledge into robotic systems remains an open challenge, given the scarcity of human-robot interactions and the lack of large-scale datasets of real-world robotic data. Previous robot learning approaches such as behavior cloning and reinforcement learning have shown great capabilities in learning robotic skills from human demonstrations or from scratch in specific environments. However, these approaches often require task-specific demonstrations or designing complex simulation environments, which limits the development of generalizable and robust policies for new settings. Aiming to address these limitations, we propose an agent-based framework for grounding robot policies to the current context, considering the constraints of a current robot and its environment using visuomotor-grounded language guidance. The proposed framework is composed of a set of conversational agents designed for specific roles--namely, high-level advisor, visual grounding, monitoring, and robotic agents. Given a base policy, the agents collectively generate guidance at run time to shift the action distribution of the base policy towards more desirable future states. We demonstrate that our approach can effectively guide manipulation policies to achieve significantly higher success rates both in simulation and in real-world experiments without the need for additional human demonstrations or extensive exploration. In recent years, the advent of foundation models, such as large-scale pre-trained language models (LLMs) and visual language models (VLMs), has shown great capabilities in understanding context, scenes, and the underlying dynamics of the world. Furthermore, emergent capabilities such as incontext learning have shown great potential in the transfer of knowledge between domains, e.g., via few-shot demonstrations or zero-shot inference.