We present the first evaluation harness that enables any out-of-the-box, local, Large Language Models (LLMs) to play full-press Diplomacy without fine-tuning or specialized training. Previous work required frontier LLMs, or fine-tuning, due to the high complexity and information density of Diplomacy's game state. Combined with the high variance of matches, these factors made Diplomacy prohibitive for study. In this work, we used data-driven iteration to optimize a textual game state representation such that a 24B model can reliably complete matches without any fine tuning. We develop tooling to facilitate hypothesis testing and statistical analysis, and we present case studies on persuasion, aggressive playstyles, and performance across a range of models. We conduct a variety of experiments across many popular LLMs, finding the larger models perform the best, but the smaller models still play adequately. We also introduce Critical State Analysis: an experimental protocol for rapidly iterating and analyzing key moments in a game at depth. Our harness democratizes the evaluation of strategic reasoning in LLMs by eliminating the need for fine-tuning, and it provides insights into how these capabilities emerge naturally from widely used LLMs. Our code is available in the supplement and will be open sourced.

Large Language Models (LLMs) often struggle to use information across long inputs effectively. Prior work has identified positional biases, such as the Lost in the Middle (LiM) effect, where models perform better when information appears at the beginning (primacy bias) or end (recency bias) of the input, rather than in the middle. However, long-context studies have not consistently replicated these effects, raising questions about their intensity and the conditions under which they manifest. To address this, we conducted a comprehensive analysis using relative rather than absolute input lengths, defined with respect to each model's context window. Our findings reveal that the LiM effect is strongest when inputs occupy up to 50% of a model's context window. Beyond that, the primacy bias weakens, while recency bias remains relatively stable. This effectively eliminates the LiM effect; instead, we observe a distance-based bias, where model performance is better when relevant information is closer to the end of the input. Furthermore, our results suggest that successful retrieval is a prerequisite for reasoning in LLMs, and that the observed positional biases in reasoning are largely inherited from retrieval. These insights have implications for long-context tasks, the design of future LLM benchmarks, and evaluation methodologies for LLMs handling extended inputs.

Language is a ubiquitous tool that is foundational to reasoning and collaboration, ranging from everyday interactions to sophisticated problem-solving tasks. The establishment of a common language can serve as a powerful asset in ensuring clear communication and understanding amongst agents, facilitating desired coordination and strategies. In this work, we extend the capabilities of large language models (LLMs) by integrating them with advancements in multi-agent decision-making algorithms. We propose a systematic framework for the design of multi-agentic large language models (LLMs), focusing on key integration practices. These include advanced prompt engineering techniques, the development of effective memory architectures, multi-modal information processing, and alignment strategies through fine-tuning algorithms. We evaluate these design choices through extensive ablation studies on classic game settings with significant underlying social dilemmas and game-theoretic considerations.

Currently, various uncertainty quantification methods have been proposed to provide certainty and probability estimates for deep learning models' label predictions. Meanwhile, with the growing demand for the right to be forgotten, machine unlearning has been extensively studied as a means to remove the impact of requested sensitive data from a pre-trained model without retraining the model from scratch. However, the vulnerabilities of such generated predictive uncertainties with regard to dedicated malicious unlearning attacks remain unexplored. To bridge this gap, for the first time, we propose a new class of malicious unlearning attacks against predictive uncertainties, where the adversary aims to cause the desired manipulations of specific predictive uncertainty results. We also design novel optimization frameworks for our attacks and conduct extensive experiments, including black-box scenarios. Notably, our extensive experiments show that our attacks are more effective in manipulating predictive uncertainties than traditional attacks that focus on label misclassifications, and existing defenses against conventional attacks are ineffective against our attacks.

Existing operator learning methods rely on supervised training with high-fidelity simulation data, introducing significant computational cost. In this work, we propose the deep Onsager operator learning (DOOL) method, a novel unsupervised framework for solving dissipative equations. Rooted in the Onsager variational principle (OVP), DOOL trains a deep operator network by directly minimizing the OVP-defined Rayleighian functional, requiring no labeled data, and then proceeds in time explicitly through conservation/change laws for the solution. Another key innovation here lies in the spatiotemporal decoupling strategy: the operator's trunk network processes spatial coordinates exclusively, thereby enhancing training efficiency, while integrated external time stepping enables temporal extrapolation. Numerical experiments on typical dissipative equations validate the effectiveness of the DOOL method, and systematic comparisons with supervised DeepONet and MIONet demonstrate its enhanced performance. Extensions are made to cover the second-order wave models with dissipation that do not directly follow OVP.

Large Language Models (LLMs) with inference-time scaling techniques show promise for code generation, yet face notable efficiency and scalability challenges. Construction-based tree-search methods suffer from rapid growth in tree size, high token consumption, and lack of anytime property. In contrast, improvement-based methods offer better performance but often struggle with uninformative reward signals and inefficient search strategies. In this work, we propose \textbf{ReLoc}, a unified local search framework which effectively performs step-by-step code revision. Specifically, ReLoc explores a series of local revisions through four key algorithmic components: initial code drafting, neighborhood code generation, candidate evaluation, and incumbent code updating, each of which can be instantiated with specific decision rules to realize different local search algorithms such as Hill Climbing (HC) or Genetic Algorithm (GA). Furthermore, we develop a specialized revision reward model that evaluates code quality based on revision distance to produce fine-grained preferences that guide the local search toward more promising candidates. Finally, our extensive experimental results demonstrate that our approach achieves superior performance across diverse code generation tasks, significantly outperforming both construction-based tree search as well as the state-of-the-art improvement-based code generation methods.

Lightning, a common feature of severe meteorological conditions, poses significant risks, from direct human injuries to substantial economic losses. These risks are further exacerbated by climate change. Early and accurate prediction of lightning would enable preventive measures to safeguard people, protect property, and minimize economic losses. In this paper, we present DeepLight, a novel deep learning architecture for predicting lightning occurrences. Existing prediction models face several critical limitations: they often struggle to capture the dynamic spatial context and inherent uncertainty of lightning events, underutilize key observational data, such as radar reflectivity and cloud properties, and rely heavily on Numerical Weather Prediction (NWP) systems, which are both computationally expensive and highly sensitive to parameter settings. To overcome these challenges, DeepLight leverages multi-source meteorological data, including radar reflectivity, cloud properties, and historical lightning occurrences through a dual-encoder architecture. By employing multi-branch convolution techniques, it dynamically captures spatial correlations across varying extents. Furthermore, its novel Hazy Loss function explicitly addresses the spatio-temporal uncertainty of lightning by penalizing deviations based on proximity to true events, enabling the model to better learn patterns amidst randomness. Extensive experiments show that DeepLight improves the Equitable Threat Score (ETS) by 18%-30% over state-of-the-art methods, establishing it as a robust solution for lightning prediction.

Leveraging Large Language Models (LLMs) to write policy code for controlling robots has gained significant attention. However, in long-horizon implicative tasks, this approach often results in API parameter, comments and sequencing errors, leading to task failure. To address this problem, we propose a collaborative Triple-S framework that involves multiple LLMs. Through In-Context Learning, different LLMs assume specific roles in a closed-loop Simplification-Solution-Summary process, effectively improving success rates and robustness in long-horizon implicative tasks. Additionally, a novel demonstration library update mechanism which learned from success allows it to generalize to previously failed tasks. We validate the framework in the Long-horizon Desktop Implicative Placement (LDIP) dataset across various baseline models, where Triple-S successfully executes 89% of tasks in both observable and partially observable scenarios. Experiments in both simulation and real-world robot settings further validated the effectiveness of Triple-S. Our code and dataset is available at: https://github.com/Ghbbbbb/Triple-S.

Agricultural robots have emerged as powerful members in agricultural tasks, nevertheless, still heavily rely on manual operation or untransportable railway for movement, resulting in limited mobility and poor adaptability. Vision-and-Language Navigation (VLN) enables robots to navigate to the target destinations following natural language instructions, demonstrating strong performance on several domains. However, none of the existing benchmarks or methods is specifically designed for agricultural scenes. To bridge this gap, we propose A griculture to A griculture ( A2A) benchmark, containing 1,560 episodes across six diverse agricultural scenes, in which all realistic RGB videos are captured by front-facing camera on a quadruped robot at a height of 0.38 meters, aligning with the practical deployment conditions. Meanwhile, we propose V ision-and-L anguage Navigation for Agricultural Robots ( AgriVLN) baseline based on Vision-Language Model (VLM) prompted with carefully crafted templates, which can understand both given instructions and agricultural environments to generate appropriate low-level actions for robot control. When evaluated on A2A, AgriVLN performs well on short instructions but struggles with long instructions, because it often fails to track which part of the instruction is currently being executed. To address this, we further propose Subt ask List ( STL) instruction decomposition module and integrate it into AgriVLN, improving Success Rate (SR) from 0.31 to 0.42. We additionally compare AgriVLN with several existing VLN methods, demonstrating the state-of-the-art performance in the agricultural domain.

Given recent breakthroughs in Generative Artificial Intelligence (GAI) and Large Language Models (LLMs), more and more professional services are being augmented through Artificial Intelligence (AI), which once seemed impossible to automate. This paper presents a modular model for leveraging GAI in developing strategic plans for large scale government organizations and evaluates leading machine learning techniques in their application towards one of the identified modules. Specifically, the performance of BERTopic and Non-negative Matrix Factorization (NMF) are evaluated in their ability to use topic modeling to generate themes representative of Vision Elements within a strategic plan. To accomplish this, BERTopic and NMF models are trained using a large volume of reports from the Government Accountability Office (GAO). The generated topics from each model are then scored for similarity against the Vision Elements of a published strategic plan and the results are compared. Our results show that these techniques are capable of generating themes similar to 100% of the elements being evaluated against. Further, we conclude that BERTopic performs best in this application with more than half of its correlated topics achieving a "medium" or "strong" correlation. A capability of GAI-enabled strategic plan development impacts a multi-billion dollar industry and assists the federal government in overcoming regulatory requirements which are crucial to the public good. Further work will focus on the operationalization of the concept proven in this study as well as viability of the remaining modules in the proposed model for GAI-generated strategic plans.