The rapid development of large language and multimodal models has sparked significant interest in using proprietary models, such as GPT-4o, to develop autonomous agents capable of handling real-world scenarios like web navigation. Although recent open-source efforts have tried to equip agents with the ability to explore environments and continuously improve over time, they are building text-only agents in synthetic environments where the reward signals are clearly defined. Such agents struggle to generalize to realistic settings that require multimodal perception abilities and lack ground-truth signals. In this paper, we introduce an open-source framework designed to facilitate the development of multimodal web agent that can autonomously conduct real-world exploration and improve itself. We first train the base model with imitation learning to gain the basic abilities. We then let the agent explore the open web and collect feedback on its trajectories. After that, it further improves its policy by learning from well-performing trajectories judged by another general-purpose model. This exploration-feedback-optimization cycle can continue for several iterations. Experimental results show that our web agent successfully improves itself after each iteration, demonstrating strong performance across multiple test sets.

Shared control problems involve a robot learning to collaborate with a human. When learning a shared control policy, short communication between the agents can often significantly reduce running times and improve the system's accuracy. We extend the shared control problem to include the ability to directly query a cooperating agent. We consider two types of potential responses to a query, namely oracles: one that can provide the learner with the best action they should take, even when that action might be myopically wrong, and one with a bounded knowledge limited to its part of the system. Given this additional information channel, this work further presents three heuristics for choosing when to query: reinforcement learning-based, utility-based, and entropy-based. These heuristics aim to reduce a system's overall learning cost. Empirical results on two environments show the benefits of querying to learn a better control policy and the tradeoffs between the proposed heuristics.

Financial intelligence generation from vast data sources has typically relied on traditional methods of knowledge-graph construction or database engineering. Recently, fine-tuned financial domain-specific Large Language Models (LLMs), have emerged. While these advancements are promising, limitations such as high inference costs, hallucinations, and the complexity of concurrently analyzing high-dimensional financial data, emerge. This motivates our invention FISHNET (Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert swarming, and Task planning), an agentic architecture that accomplishes highly complex analytical tasks for more than 98,000 regulatory filings that vary immensely in terms of semantics, data hierarchy, or format. FISHNET shows remarkable performance for financial insight generation (61.8% success rate over 5.0% Routing, 45.6% RAG R-Precision). We conduct rigorous ablations to empirically prove the success of FISHNET, each agent's importance, and the optimized performance of assembling all agents. Our modular architecture can be leveraged for a myriad of use-cases, enabling scalability, flexibility, and data integrity that are critical for financial tasks.

Designing effective two-sided matching mechanisms is a major problem in mechanism design, and the goodness of matching cannot always be formulated. The existing work addresses this issue by searching over a parameterized family of mechanisms with certain properties by learning to fit a human-crafted dataset containing examples of preference profiles and matching results. However, this approach does not consider a strategy-proof mechanism, implicitly assumes the number of agents to be a constant, and does not consider the public contextual information of the agents. In this paper, we propose a new parametric family of strategy-proof matching mechanisms by extending the serial dictatorship (SD). We develop a novel attention-based neural network called NeuralSD, which can learn a strategy-proof mechanism from a human-crafted dataset containing public contextual information. NeuralSD is constructed by tensor operations that make SD differentiable and learns a parameterized mechanism by estimating an order of SD from the contextual information. We conducted experiments to learn a strategy-proof matching from matching examples with different numbers of agents. We demonstrated that our method shows the superiority of learning with context-awareness over a baseline in terms of regression performance and other metrics.

Language agents have recently been used to simulate human behavior and user-item interactions for recommendation systems. However, current language agent simulations do not understand the relationships between users and items, leading to inaccurate user profiles and ineffective recommendations. In this work, we explore the utility of Knowledge Graphs (KGs), which contain extensive and reliable relationships between users and items, for recommendation. Our key insight is that the paths in a KG can capture complex relationships between users and items, eliciting the underlying reasons for user preferences and enriching user profiles. Leveraging this insight, we propose Knowledge Graph Enhanced Language Agents(KGLA), a framework that unifies language agents and KG for recommendation systems. In the simulated recommendation scenario, we position the user and item within the KG and integrate KG paths as natural language descriptions into the simulation. This allows language agents to interact with each other and discover sufficient rationale behind their interactions, making the simulation more accurate and aligned with real-world cases, thus improving recommendation performance. Our experimental results show that KGLA significantly improves recommendation performance (with a 33%-95% boost in NDCG@1 among three widely used benchmarks) compared to the previous best baseline method.

Enhancing the reasoning capabilities of large language models (LLMs) is crucial for enabling them to tackle complex, multi-step problems. Multi-agent frameworks have shown great potential in enhancing LLMs' reasoning capabilities. However, the lack of effective cooperation between LLM agents hinders their performance, especially for multi-step reasoning tasks. This paper proposes a novel cooperative multi-agent reasoning framework (CoPlanner) by separating reasoning steps and assigning distinct duties to different agents. CoPlanner consists of two LLM agents: a planning agent and a reasoning agent. The planning agent provides high-level strategic hints, while the reasoning agent follows these hints and infers answers. By training the planning agent's policy through the interactive reasoning process via Proximal Policy Optimization (PPO), the LLaMA-3-8B-based CoPlanner outperforms the previous best method by 9.94\% on LogiQA and 3.09\% on BBH. Our results demonstrate that the guidance from the planning agent and the effective cooperation between the agents contribute to the superior performance of CoPlanner in tackling multi-step reasoning problems.

Analyzing and forecasting trajectories of agents like pedestrians plays a pivotal role for embodied intelligent applications. The inherent indeterminacy of human behavior and complex social interaction among a rich variety of agents make this task more challenging than common time-series forecasting. In this letter, we aim to explore a distinct formulation for multi-agent trajectory prediction framework. Specifically, we proposed a patching-based temporal feature extraction module and a graph-based social feature extraction module, enabling effective feature extraction and cross-scenario generalization. Moreover, we reassess the role of social interaction and present a novel method based on explicit modality modulation to integrate temporal and social features, thereby constructing an efficient single-stage inference pipeline. Results on public benchmark datasets demonstrate the superior performance of our model compared with the state-of-the-art methods. The code is available at: github.com/TIB-K330/pmm-net.

In this interview series, we're meeting some of the AAAI/SIGAI Doctoral Consortium participants to find out more about their research. The Doctoral Consortium provides an opportunity for a group of PhD students to discuss and explore their research interests and career objectives in an interdisciplinary workshop together with a panel of established researchers. In this latest interview, we hear from Pulkit Verma, recent PhD graduate from Arizona State University. I recently completed my PhD in Computer Science from School of Computing and Augmented Intelligence, Arizona State University. My research focuses on safe and reliable behavior of AI agents.

With the growing spread of misinformation online, research has increasingly focused on detecting and tracking fake news. However, an overlooked issue is that fake news does not naturally exist in social networks -- it often originates from distorted facts or deliberate fabrication by malicious actors. Understanding how true news gradually evolves into fake news is critical for early detection and prevention, reducing its spread and impact. Hence, in this paper, we take the first step toward simulating and revealing this evolution, proposing a Fake News evolUtion Simulation framEwork (FUSE) based on large language models (LLMs). Specifically, we employ LLM as agents to represent individuals in a simulated social network. We define four types of agents commonly observed in daily interactions: spreaders, who propagate information; commentators, who provide opinions and interpretations; verifiers, who check the accuracy of information; and bystanders, who passively observe without engaging. For simulated environments, we model various social network structures, such as high-clustering networks and scale-free networks, to mirror real-world network dynamics. Each day, the agents engage in belief exchanges, reflect on their thought processes, and reintroduce the news accordingly. Given the lack of prior work in this area, we developed a FUSE-EVAL evaluation framework to measure the deviation from true news during the fake news evolution process. The results show that FUSE successfully captures the underlying patterns of how true news transforms into fake news and accurately reproduces previously discovered instances of fake news, aligning closely with human evaluations. Moreover, our work provides insights into the fact that combating fake news should not be delayed until it has fully evolved; instead, prevention in advance is key to achieving better outcomes.

Robotic cloth manipulation faces challenges due to the fabric's complex dynamics and the high dimensionality of configuration spaces. Previous methods have largely focused on isolated smoothing or folding tasks and overly reliant on simulations, often failing to bridge the significant sim-to-real gap in deformable object manipulation. To overcome these challenges, we propose a two-stream architecture with sequential and spatial pathways, unifying smoothing and folding tasks into a single adaptable policy model that accommodates various cloth types and states. The sequential stream determines the pick and place positions for the cloth, while the spatial stream, using a connectivity dynamics model, constructs a visibility graph from partial point cloud data of the self-occluded cloth, allowing the robot to infer the cloth's full configuration from incomplete observations. To bridge the sim-to-real gap, we utilize a hand tracking detection algorithm to gather and integrate human demonstration data into our novel end-to-end neural network, improving real-world adaptability. Our method, validated on a UR5 robot across four distinct cloth folding tasks with different goal shapes, consistently achieves folded states from arbitrary crumpled initial configurations, with success rates of 99\%, 99\%, 83\%, and 67\%. It outperforms existing state-of-the-art cloth manipulation techniques and demonstrates strong generalization to unseen cloth with diverse colors, shapes, and stiffness in real-world experiments.Videos and source code are available at: https://zcswdt.github.io/SSFold/