Geometry optimization of atomic structures is a common and crucial task in computational chemistry and materials design. Following the learning to optimize paradigm, we propose a new multi-agent reinforcement learning method called Multi-Agent Crystal Structure optimization (MACS) to address periodic crystal structure optimization. MACS treats geometry optimization as a partially observable Markov game in which atoms are agents that adjust their positions to collectively discover a stable configuration. We train MACS across various compositions of reported crystalline materials to obtain a policy that successfully optimizes structures from the training compositions as well as structures of larger sizes and unseen compositions, confirming its excellent scalability and zero-shot transferability. We benchmark our approach against a broad range of state-of-the-art optimization methods and demonstrate that MACS optimizes periodic crystal structures significantly faster, with fewer energy calculations, and the lowest failure rate.

Ensuring the safety of reinforcement learning (RL) policies in high-stakes environments requires not only formal verification but also interpretability and targeted falsification. While model checking provides formal guarantees, its effectiveness is limited by abstraction quality and the completeness of the underlying trajectory dataset. We propose a hybrid framework that integrates (1) explainability, (2) model checking, and (3) risk-guided falsification to achieve both rigor and coverage. Our approach begins by constructing a human-interpretable abstraction of the RL policy using Comprehensible Abstract Policy Summarization (CAPS). This abstract graph, derived from offline trajectories, is both verifier-friendly, semantically meaningful, and can be used as input to Storm probabilistic model checker to verify satisfaction of temporal safety specifications. If the model checker identifies a violation, it will return an interpretable counterexample trace by which the policy fails the safety requirement. However, if no violation is detected, we cannot conclude satisfaction due to potential limitation in the abstraction and coverage of the offline dataset. In such cases, we estimate associated risk during model checking to guide a falsification strategy that prioritizes searching in high-risk states and regions underrepresented in the trajectory dataset. We further provide PAC-style guarantees on the likelihood of uncovering undetected violations. Finally, we incorporate a lightweight safety shield that switches to a fallback policy at runtime when such a risk exceeds a threshold, facilitating failure mitigation without retraining.

Instruction fine-tuning is crucial in NLP tasks, enhancing pretrained models' instruction-following capabilities and task-specific performance. However, obtaining high-quality fine-tuning data for large models is challenging due to data collection difficulties and high production costs. To address this, we propose MASTER, a novel data augmentation method that enriches original data through interactions among multiple agents with varying cognitive levels. We simulate three pedagogically grounded teaching scenarios, leveraging multi-agent conversations to generate high-quality teacher-student interaction data. Utilizing MASTER, we construct BOOST-QA, a fine-tuning dataset augmented from existing datasets like Orca-Math-200k, ProcQA, and OpenHermes2.5. Experiments show that models fine-tuned with BOOST-QA perform excellently across multiple benchmarks, demonstrating strong multitask generalization. Notably, MASTER significantly improves models' reasoning abilities in complex tasks, providing valuable insights for future research.

Entity relationship classification remains a challenging task in information extraction, especially in scenarios with limited labeled data and complex relational structures. In this study, we conduct a comparative analysis of three distinct AI agent architectures designed to perform relation classification using large language models (LLMs). The agentic architectures explored include (1) reflective self-evaluation, (2) hierarchical task decomposition, and (3) a novel multi-agent dynamic example generation mechanism, each leveraging different modes of reasoning and prompt adaptation. In particular, our dynamic example generation approach introduces real-time cooperative and adversarial prompting. We systematically compare their performance across multiple domains and model backends. Our experiments demonstrate that multi-agent coordination consistently outperforms standard few-shot prompting and approaches the performance of fine-tuned models. These findings offer practical guidance for the design of modular, generalizable LLM-based systems for structured relation extraction. The source codes and dataset are available at https://github.com/maryambrj/ALIEN.git.

--RF/Analog design is essential for bridging digital technologies with real-world signals, ensuring the functionality and reliability of a wide range of electronic systems. However, analog design procedures are often intricate, time-consuming and reliant on expert intuition, and hinder the time and cost efficiency of circuit development. T o overcome the limitations of the manual circuit design, we introduce MenT eR - a multi-agent workflow integrated into an end-to-end analog design framework. By employing multiple specialized AI agents that collaboratively address different aspects of the design process, such as specification understanding, circuit optimization, and test bench validation, MenT eR reduces the dependency on frequent trial-and-error-style intervention. MenT eR not only accelerates the design cycle time but also facilitates a broader exploration of the design space, demonstrating robust capabilities in handling real-world analog systems. We believe that MenT eR lays the groundwork for future "RF/Analog Copilots" that can collaborate seamlessly with human designers. The recent progress of Large Language Models (LLMs) has led to an increasing numbers of LLM applications in scientific and engineering fields such as mathematical reasoning, pharmaceutical development, and chip design. For instance, in the field of digital circuit design, Liu et al. [1] introduced the first domain-adapted LLM, which demonstrated the potential of using legacy chip design documents to increase the design capabilities of LLM.

Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) are known to be NEXP-Complete and intractable to solve. However, for problems such as cooperative navigation, obstacle avoidance, and formation control, basic assumptions can be made about local visibility and local dependencies. The work DeWeese and Qu 2024 formalized these assumptions in the construction of the Locally Interdependent Multi-Agent MDP. In this setting, it establishes three closed-form policies that are tractable to compute in various situations and are exponentially close to optimal with respect to visibility. However, it is also shown that these solutions can have poor performance when the visibility is small and fixed, often getting stuck during simulations due to the so called "Penalty Jittering" phenomenon. In this work, we establish the Extended Cutoff Policy Class which is, to the best of our knowledge, the first non-trivial class of near optimal closed-form partially observable policies that are exponentially close to optimal with respect to the visibility for any Locally Interdependent Multi-Agent MDP. These policies are able to remember agents beyond their visibilities which allows them to perform significantly better in many small and fixed visibility settings, resolve Penalty Jittering occurrences, and under certain circumstances guarantee fully observable joint optimal behavior despite the partial observability. We also propose a generalized form of the Locally Interdependent Multi-Agent MDP that allows for transition dependence and extended reward dependence, then replicate our theoretical results in this setting.

Courtrooms are places where lives are determined and fates are sealed, yet they are not impervious to manipulation. Strategic use of manipulation in legal jargon can sway the opinions of judges and affect the decisions. Despite the growing advancements in NLP, its application in detecting and analyzing manipulation within the legal domain remains largely unexplored. Our work addresses this gap by introducing LegalCon, a dataset of 1,063 annotated courtroom conversations labeled for manipulation detection, identification of primary manipulators, and classification of manipulative techniques, with a focus on long conversations. Furthermore, we propose CLAIM, a two-stage, Intent-driven Multi-agent framework designed to enhance manipulation analysis by enabling context-aware and informed decision-making. Our results highlight the potential of incorporating agentic frameworks to improve fairness and transparency in judicial processes. We hope that this contributes to the broader application of NLP in legal discourse analysis and the development of robust tools to support fairness in legal decision-making. Our code and data are available at https://github.com/Disha1001/CLAIM.

It offers a compelling framework for scenarios in which data cannot be centrally aggregated due to privacy constraints, thereby promoting compliance with data protection regulations and enhancing scalability [1]. Beyond its foundational role in privacy-preserving learning, FL also facilitates model personalization--adapting learning outcomes to individual users across the network--an increasingly relevant objective given the heterogeneity of user behavior and datasets. A comprehensive overview of the challenges and practical implementations of personalized federated learning is presented in [2]. Despite its broad applicability, particularly in contexts with stringent data privacy constraints, FL introduces a set of constraints that must be carefully addressed to ensure robust and efficient model training. These constraints include limited communication bandwidth, restricted computation at edge devices, privacy preservation requirements, and data heterogeneity and imbalance. Dataset imbalance in FL emerges when edge devices possess non-uniform class distributions, disparate dataset sizes, or varying data quality [3, 4]. In this work, we propose a preprocessing framework that addresses this imbalance challenge in a model-and algorithm-agnostic manner. Our method aligns and transforms local datasets into a shared representation space that captures statistical information from all participating agents in the network.

Multi-objective reinforcement learning (MORL) aims at optimising several, often conflicting goals in order to improve flexibility and reliability of RL in practical tasks. This can be achieved by finding diverse policies that are optimal for some objective preferences and non-dominated by optimal policies for other preferences so that they form a Pareto front in the multi-objective performance space. The relation between the multi-objective performance space and the parameter space that represents the policies is generally non-unique. Using a training scheme that is based on a locally linear map between the parameter space and the performance space, we show that an approximate Pareto front can provide an interpretation of the current parameter vectors in terms of the objectives which enables an effective search within contiguous solution domains. Experiments are conducted with and without retraining across different domains, and the comparison with previous methods demonstrates the efficiency of our approach.

We investigate the problem of learning an equilibrium in a generalized two-sided matching market, where agents can adaptively choose their actions based on their assigned matches. Specifically, we consider a setting in which matched agents engage in a zero-sum game with initially unknown payoff matrices, and we explore whether a centralized procedure can learn an equilibrium from bandit feedback. We adopt the solution concept of matching equilibrium, where a pair consisting of a matching $\mathfrak{m}$ and a set of agent strategies $X$ forms an equilibrium if no agent has the incentive to deviate from $(\mathfrak{m}, X)$. To measure the deviation of a given pair $(\mathfrak{m}, X)$ from the equilibrium pair $(\mathfrak{m}^\star, X^\star)$, we introduce matching instability that can serve as a regret measure for the corresponding learning problem. We then propose a UCB algorithm in which agents form preferences and select actions based on optimistic estimates of the game payoffs, and prove that it achieves sublinear, instance-independent regret over a time horizon $T$.