As increasingly capable agents are deployed, a central safety question is how to retain meaningful human control without modifying the underlying system. We study a minimal control interface where an agent chooses whether to act autonomously (play) or defer (ask), while a human simultaneously chooses whether to be permissive (trust) or to engage in oversight (oversee). If the agent defers, the human's choice determines the outcome, potentially leading to a corrective action or a system shutdown. We model this interaction as a two-player Markov Game. Our analysis focuses on cases where this game qualifies as a Markov Potential Game (MPG), a class of games where we can provide an alignment guarantee: under a structural assumption on the human's value function, any decision by the agent to act more autonomously that benefits itself cannot harm the human's value. We also analyze extensions to this MPG framework. Theoretically, this perspective provides conditions for a specific form of intrinsic alignment. If the reward structures of the human-agent game meet these conditions, we have a formal guarantee that the agent improving its own outcome will not harm the human's. Practically, this model motivates a transparent control layer with predictable incentives where the agent learns to defer when risky and act when safe, while its pretrained policy and the environment's reward structure remain untouched. Our gridworld simulation shows that through independent learning, the agent and human discover their optimal oversight roles. The agent learns to ask when uncertain and the human learns when to oversee, leading to an emergent collaboration that avoids safety violations introduced post-training. This demonstrates a practical method for making misaligned models safer after deployment.

Abstract--Conventional robots possess a limited understanding of their kinematics and are confined to preprogrammed tasks, hindering their ability to leverage tools efficiently. Driven by the essential components of tool usage--grasping the desired outcome, selecting the most suitable tool, determining optimal tool orientation, and executing precise manipulations--we introduce a pioneering framework. Our novel approach expands the capabilities of the robot's inverse kinematics solver, empowering it to acquire a sequential repertoire of actions using tools of varying lengths. By integrating a simulation-learned action trajectory with the tool, we showcase the practicality of transferring acquired skills from simulation to real-world scenarios through comprehensive experimentation. Remarkably, our extended inverse kinematics solver demonstrates an impressive error rate of less than 1cm. Furthermore, our trained policy achieves a mean error of 8cm in simulation. Noteworthy, our model achieves virtually indistinguishable performance when employing two distinct tools of different lengths. This research provides an indication of potential advances in the exploration of all four fundamental aspects of tool usage, enabling robots to master the intricate art of tool manipulation across diverse tasks. Tool use is the employment of a device or object held in a robotic gripper or hand to fulfill a task goal. Humans and animals like the New Caledonian crow have learned to use tools to accomplish tasks that they were not previously able to do when using only their own bodies or appendages.

Public resource allocation involves the efficient distribution of resources, including urban infrastructure, energy, and transportation, to effectively meet societal demands. However, existing methods focus on optimizing the movement of individual resources independently, without considering their capacity constraints. To address this limitation, we propose a novel and more practical problem: Collaborative Public Resource Allocation (CPRA), which explicitly incorporates capacity constraints and spatio-temporal dynamics in real-world scenarios. We propose a new framework called Game-Theoretic Spatio-Temporal Reinforcement Learning (GSTRL) for solving CPRA. Our contributions are twofold: 1) We formulate the CPRA problem as a potential game and demonstrate that there is no gap between the potential function and the optimal target, laying a solid theoretical foundation for approximating the Nash equilibrium of this NP-hard problem; and 2) Our designed GSTRL framework effectively captures the spatio-temporal dynamics of the overall system. We evaluate GSTRL on two real-world datasets, where experiments show its superior performance. Our source codes are available in the supplementary materials.

Large Language Models (LLMs) often struggle with problems that require multi-step reasoning. For small-scale open-source models, Reinforcement Learning with Verifiable Rewards (RLVR) fails when correct solutions are rarely sampled even after many attempts, while Supervised Fine-Tuning (SFT) tends to overfit long demonstrations through rigid token-by-token imitation. To address this gap, we propose Supervised Reinforcement Learning (SRL), a framework that reformulates problem solving as generating a sequence of logical "actions". SRL trains the model to generate an internal reasoning monologue before committing to each action. It provides smoother rewards based on the similarity between the model's actions and expert actions extracted from the SFT dataset in a step-wise manner. This supervision offers richer learning signals even when all rollouts are incorrect, while encouraging flexible reasoning guided by expert demonstrations. As a result, SRL enables small models to learn challenging problems previously unlearnable by SFT or RLVR. Moreover, initializing training with SRL before refining with RLVR yields the strongest overall performance. Beyond reasoning benchmarks, SRL generalizes effectively to agentic software engineering tasks, establishing it as a robust and versatile training framework for reasoning-oriented LLMs.

People's goal-directed behaviors are influenced by their cognitive biases, and autonomous systems that interact with people should be aware of this. For example, people's attention to objects in their environment will be biased in a way that systematically affects how they perform everyday tasks such as driving to work. Here, building on recent work in computational cognitive science, we formally articulate the attention-aware inverse planning problem, in which the goal is to estimate a person's attentional biases from their actions. We demonstrate how attention-aware inverse planning systematically differs from standard inverse reinforcement learning and how cognitive biases can be inferred from behavior. Finally, we present an approach to attention-aware inverse planning that combines deep reinforcement learning with computational cognitive modeling. We use this approach to infer the attentional strategies of RL agents in real-life driving scenarios selected from the Waymo Open Dataset, demonstrating the scalability of estimating cognitive biases with attention-aware inverse planning.

Algorithmic collusion has emerged as a central question in AI: Will the interaction between different AI agents deployed in markets lead to collusion? More generally, understanding how emergent behavior, be it a cartel or market dominance from more advanced bots, affects the market overall is an important research question. We propose a hierarchical multi-agent reinforcement learning framework to study algorithmic collusion in market making. The framework includes a self-interested market maker (Agent~A), which is trained in an uncertain environment shaped by an adversary, and three bottom-layer competitors: the self-interested Agent~B1 (whose objective is to maximize its own PnL), the competitive Agent~B2 (whose objective is to minimize the PnL of its opponent), and the hybrid Agent~B$^\star$, which can modulate between the behavior of the other two. To analyze how these agents shape the behavior of each other and affect market outcomes, we propose interaction-level metrics that quantify behavioral asymmetry and system-level dynamics, while providing signals potentially indicative of emergent interaction patterns. Experimental results show that Agent~B2 secures dominant performance in a zero-sum setting against B1, aggressively capturing order flow while tightening average spreads, thus improving market execution efficiency. In contrast, Agent~B$^\star$ exhibits a self-interested inclination when co-existing with other profit-seeking agents, securing dominant market share through adaptive quoting, yet exerting a milder adverse impact on the rewards of Agents~A and B1 compared to B2. These findings suggest that adaptive incentive control supports more sustainable strategic co-existence in heterogeneous agent environments and offers a structured lens for evaluating behavioral design in algorithmic trading systems.

Ride-pooling, also known as ride-sharing, shared ride-hailing, or microtransit, is a service wherein passengers share rides. This service can reduce costs for both passengers and operators and reduce congestion and environmental impacts. A key limitation, however, is its myopic decision-making, which overlooks long-term effects of dispatch decisions. To address this, we propose a simulation-informed reinforcement learning (RL) approach. While RL has been widely studied in the context of ride-hailing systems, its application in ride-pooling systems has been less explored. In this study, we extend the learning and planning framework of Xu et al. (2018) from ride-hailing to ride-pooling by embedding a ride-pooling simulation within the learning mechanism to enable non-myopic decision-making. In addition, we propose a complementary policy for rebalancing idle vehicles. By employing n-step temporal difference learning on simulated experiences, we derive spatiotemporal state values and subsequently evaluate the effectiveness of the non-myopic policy using NYC taxi request data. Results demonstrate that the non-myopic policy for matching can increase the service rate by up to 8.4% versus a myopic policy while reducing both in-vehicle and wait times for passengers. Furthermore, the proposed non-myopic policy can decrease fleet size by over 25% compared to a myopic policy, while maintaining the same level of performance, thereby offering significant cost savings for operators. Incorporating rebalancing operations into the proposed framework cuts wait time by up to 27.3%, in-vehicle time by 12.5%, and raises service rate by 15.1% compared to using the framework for matching decisions alone at the cost of increased vehicle minutes traveled per passenger.

Card games are widely used to study sequential decision-making under uncertainty, with real-world analogues in negotiation, finance, and cybersecurity. These games typically fall into three categories based on the flow of control: strictly sequential (players alternate single actions), deterministic response (some actions trigger a fixed outcome), and unbounded reciprocal response (alternating counterplays are permitted). A less-explored but strategically rich structure is the bounded one-sided response, where a player's action briefly transfers control to the opponent, who must satisfy a fixed condition through one or more moves before the turn resolves. We term games featuring this mechanism Bounded One-Sided Response Games (BORGs). We introduce a modified version of Monopoly Deal as a benchmark environment that isolates this dynamic, where a Rent action forces the opponent to choose payment assets. The gold-standard algorithm, Counterfactual Regret Minimization (CFR), converges on effective strategies without novel algorithmic extensions. A lightweight full-stack research platform unifies the environment, a parallelized CFR runtime, and a human-playable web interface. The trained CFR agent and source code are available at https://monopolydeal.ai.

Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs). However, existing training algorithms such as SFT, PPO, and GRPO may not generalize well across unseen reasoning tasks and heavily rely on a biased reward model. To address this challenge, we reformulate reasoning in LVLMs as posterior inference and propose a scalable training algorithm based on amortized variational inference. By leveraging diversity-seeking reinforcement learning algorithms, we introduce a novel sparse reward function for token-level learning signals that encourage diverse, high-likelihood latent CoT, overcoming deterministic sampling limitations and avoiding reward hacking. Additionally, we implement a Bayesian inference-scaling strategy that replaces costly Best-of-N and Beam Search with a marginal likelihood to efficiently rank optimal rationales and answers. We empirically demonstrate that the proposed method enhances the state-of-the-art LVLMs on seven reasoning benchmarks, in terms of effectiveness, generalization, and interpretability.

While several high profile video games have served as testbeds for Deep Reinforcement Learning (DRL), this technique has rarely been employed by the game industry for crafting authentic AI behaviors. Previous research focuses on training super-human agents with large models, which is impractical for game studios with limited resources aiming for human-like agents. This paper proposes a sample-efficient DRL method tailored for training and fine-tuning agents in industrial settings such as the video game industry. Our method improves sample efficiency of value-based DRL by leveraging pre-collected data and increasing network plasticity. We evaluate our method training a goalkeeper agent in EA SPORTS FC 25, one of the best-selling football simulations today. Our agent outperforms the game's built-in AI by 10% in ball saving rate. Ablation studies show that our method trains agents 50% faster compared to standard DRL methods. Finally, qualitative evaluation from domain experts indicates that our approach creates more human-like gameplay compared to hand-crafted agents. As a testament to the impact of the approach, the method has been adopted for use in the most recent release of the series.