Consensus-based Decentralized Multi-agent Reinforcement Learning for Random Access Network Optimization

With wireless devices increasingly forming a unified smart network for seamless, user-friendly operations, random access (RA) medium access control (MAC) design is considered a key solution for handling unpredictable data traffic from multiple terminals. However, it remains challenging to design an effective RA-based MAC protocol to minimize collisions and ensure transmission fairness across the devices. While existing multi-agent reinforcement learning (MARL) approaches with centralized training and decentralized execution (CTDE) have been proposed to optimize RA performance, their reliance on centralized training and the significant overhead required for information collection can make real-world applications unrealistic. In this work, we adopt a fully decentralized MARL architecture, where policy learning does not rely on centralized tasks but leverages consensus-based information exchanges across devices. We design our MARL algorithm over an actor-critic (AC) network and propose exchanging only local rewards to minimize communication overhead. Furthermore, we provide a theoretical proof of global convergence for our approach. Numerical experiments show that our proposed MARL algorithm can significantly improve RA network performance compared to other baselines.

Foundation Models for Logistics: Toward Certifiable, Conversational Planning Interfaces

Logistics operators, from battlefield coordinators rerouting airlifts ahead of a storm to warehouse managers juggling late trucks, often face life-critical decisions that demand both domain expertise and rapid and continuous replanning. While popular methods like integer programming yield logistics plans that satisfy user-defined logical constraints, they are slow and assume an idealized mathematical model of the environment that does not account for uncertainty. On the other hand, large language models (LLMs) can handle uncertainty and promise to accelerate replanning while lowering the barrier to entry by translating free-form utterances into executable plans, yet they remain prone to misinterpretations and hallucinations that jeopardize safety and cost. We introduce a neurosymbolic framework that pairs the accessibility of natural-language dialogue with verifiable guarantees on goal interpretation. It converts user requests into structured planning specifications, quantifies its own uncertainty at the field and token level, and invokes an interactive clarification loop whenever confidence falls below an adaptive threshold. A lightweight model, fine-tuned on just 100 uncertainty-filtered examples, surpasses the zero-shot performance of GPT-4.1 while cutting inference latency by nearly 50%. These preliminary results highlight a practical path toward certifiable, real-time, and user-aligned decision-making for complex logistics.

Efficient Neuro-Symbolic Retrieval-Augmented Generation through Adaptive Query Routing

Retrieval-Augmented Generation (RAG) systems address factual inconsistencies in Large Language Models by grounding generation in external knowledge, yet they face a fundamental efficiency problem: simple queries consume computational resources equivalent to complex multi-hop reasoning tasks. We present SymRAG, a neuro-symbolic framework that introduces adaptive query routing based on real-time complexity and system load assessments. SymRAG dynamically selects symbolic, neural, or hybrid processing paths to align resource use with query demands. Evaluated on 2,000 queries from HotpotQA and DROP using Llama-3.2-3B and Mistral-7B models, SymRAG achieves 97.6--100.0% exact match accuracy with significantly lower CPU utilization (3.6--6.2%) and processing time (0.985--3.165s). Disabling adaptive logic results in 169--1151% increase in processing time, highlighting the framework's impact. These results underscore the potential of adaptive neuro-symbolic routing for scalable, sustainable AI systems.

TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision

We address the problem of video question answering (video QA) with temporal grounding in a weakly supervised setup, without any temporal annotations. Given a video and a question, we generate an open-ended answer grounded with the start and end time. For this task, we propose TOGA: a vision-language model for Temporally Grounded Open-Ended Video QA with Weak Supervision. We instruct-tune TOGA to jointly generate the answer and the temporal grounding. We operate in a weakly supervised setup where the temporal grounding annotations are not available. We generate pseudo labels for temporal grounding and ensure the validity of these labels by imposing a consistency constraint between the question of a grounding response and the response generated by a question referring to the same temporal segment. We notice that jointly generating the answers with the grounding improves performance on question answering as well as grounding. We evaluate TOGA on grounded QA and open-ended QA tasks. For grounded QA, we consider the NExT-GQA benchmark which is designed to evaluate weakly supervised grounded question answering. For open-ended QA, we consider the MSVD-QA and ActivityNet-QA benchmarks. We achieve state-of-the-art performance for both tasks on these benchmarks.

Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning

Actor-critic methods for decentralized multi-agent reinforcement learning (MARL) facilitate collaborative optimal decision making without centralized coordination, thus enabling a wide range of applications in practice. To date, however, most theoretical convergence studies for existing actor-critic decentralized MARL methods are limited to the guarantee of a stationary solution under the linear function approximation. This leaves a significant gap between the highly successful use of deep neural actor-critic for decentralized MARL in practice and the current theoretical understanding. To bridge this gap, in this paper, we make the first attempt to develop a deep neural actor-critic method for decentralized MARL, where both the actor and critic components are inherently non-linear. We show that our proposed method enjoys a global optimality guarantee with a finite-time convergence rate of O(1/T), where T is the total iteration times. This marks the first global convergence result for deep neural actor-critic methods in the MARL literature. We also conduct extensive numerical experiments, which verify our theoretical results.

A Dataless Reinforcement Learning Approach to Rounding Hyperplane Optimization for Max-Cut

The Maximum Cut (MaxCut) problem is NP-Complete, and obtaining its optimal solution is NP-hard in the worst case. As a result, heuristic-based algorithms are commonly used, though their design often requires significant domain expertise. More recently, learning-based methods trained on large (un)labeled datasets have been proposed; however, these approaches often struggle with generalizability and scalability. A well-known approximation algorithm for MaxCut is the Goemans-Williamson (GW) algorithm, which relaxes the Quadratic Unconstrained Binary Optimization (QUBO) formulation into a semidefinite program (SDP). The GW algorithm then applies hyperplane rounding by uniformly sampling a random hyperplane to convert the SDP solution into binary node assignments. In this paper, we propose a training-data-free approach based on a non-episodic reinforcement learning formulation, in which an agent learns to select improved rounding hyperplanes that yield better cuts than those produced by the GW algorithm. By optimizing over a Markov Decision Process (MDP), our method consistently achieves better cuts across large-scale graphs with varying densities and degree distributions.

From Abstraction to Reality: DARPA's Vision for Robust Sim-to-Real Autonomy

The DARPA Transfer from Imprecise and Abstract Models to Autonomous Technologies (TIAMAT) program aims to address rapid and robust transfer of autonomy technologies across dynamic and complex environments, goals, and platforms. Existing methods for simulation-to-reality (sim-to-real) transfer often rely on high-fidelity simulations and struggle with broad adaptation, particularly in time-sensitive scenarios. Although many approaches have shown incredible performance at specific tasks, most techniques fall short when posed with unforeseen, complex, and dynamic real-world scenarios due to the inherent limitations of simulation. In contrast to current research that aims to bridge the gap between simulation environments and the real world through increasingly sophisticated simulations and a combination of methods typically assuming a small sim-to-real gap -- such as domain randomization, domain adaptation, imitation learning, meta-learning, policy distillation, and dynamic optimization -- TIAMAT takes a different approach by instead emphasizing transfer and adaptation of the autonomy stack directly to real-world environments by utilizing a breadth of low(er)-fidelity simulations to create broadly effective sim-to-real transfers. By abstractly learning from multiple simulation environments in reference to their shared semantics, TIAMAT's approaches aim to achieve abstract-to-real transfer for effective and rapid real-world adaptation. Furthermore, this program endeavors to improve the overall autonomy pipeline by addressing the inherent challenges in translating simulated behaviors into effective real-world performance.

A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models

Deep Reinforcement Learning (RL) has been explored and verified to be effective in solving decision-making tasks in various domains, such as robotics, transportation, recommender systems, etc. It learns from the interaction with environments and updates the policy using the collected experience. However, due to the limited real-world data and unbearable consequences of taking detrimental actions, the learning of RL policy is mainly restricted within the simulators. This practice guarantees safety in learning but introduces an inevitable sim-to-real gap in terms of deployment, thus causing degraded performance and risks in execution. There are attempts to solve the sim-to-real problems from different domains with various techniques, especially in the era with emerging techniques such as large foundations or language models that have cast light on the sim-to-real. This survey paper, to the best of our knowledge, is the first taxonomy that formally frames the sim-to-real techniques from key elements of the Markov Decision Process (State, Action, Transition, and Reward). Based on the framework, we cover comprehensive literature from the classic to the most advanced methods including the sim-to-real techniques empowered by foundation models, and we also discuss the specialties that are worth attention in different domains of sim-to-real problems. Then we summarize the formal evaluation process of sim-to-real performance with accessible code or benchmarks. The challenges and opportunities are also presented to encourage future exploration of this direction. We are actively maintaining a to include the most up-to-date sim-to-real research outcomes to help the researchers in their work.

ANSR-DT: An Adaptive Neuro-Symbolic Learning and Reasoning Framework for Digital Twins

In this paper, we propose an Adaptive Neuro-Symbolic Learning Framework for digital twin technology called ``ANSR-DT." Our approach combines pattern recognition algorithms with reinforcement learning and symbolic reasoning to enable real-time learning and adaptive intelligence. This integration enhances the understanding of the environment and promotes continuous learning, leading to better and more effective decision-making in real-time for applications that require human-machine collaboration. We evaluated the \textit{ANSR-DT} framework for its ability to learn and adapt to dynamic patterns, observing significant improvements in decision accuracy, reliability, and interpretability when compared to existing state-of-the-art methods. However, challenges still exist in extracting and integrating symbolic rules in complex environments, which limits the full potential of our framework in heterogeneous settings. Moreover, our ongoing research aims to address this issue in the future by ensuring seamless integration of neural models at large. In addition, our open-source implementation promotes reproducibility and encourages future research to build on our foundational work.

Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment

With the widespread deployment of Multimodal Large Language Models (MLLMs) for visual-reasoning tasks, improving their safety has become crucial. Recent research indicates that despite training-time safety alignment, these models remain vulnerable to jailbreak attacks: carefully crafted image-prompt pairs that compel the model to generate harmful content. In this work, we first highlight a critical safety gap, demonstrating that alignment achieved solely through safety training may be insufficient against jailbreak attacks. To address this vulnerability, we propose Immune, an inference-time defense framework that leverages a safe reward model during decoding to defend against jailbreak attacks. Additionally, we provide a rigorous mathematical characterization of Immune, offering provable guarantees against jailbreaks. Extensive evaluations on diverse jailbreak benchmarks using recent MLLMs reveal that Immune effectively enhances model safety while preserving the model's original capabilities. For instance, against text-based jailbreak attacks on LLaVA-1.6, Immune reduces the attack success rate by 57.82% and 16.78% compared to the base MLLM and state-of-the-art defense strategy, respectively.