LLM-based multi-agent systems demonstrate great potential for tackling complex problems, but how competition shapes their behavior remains underexplored. This paper investigates the over-competition in multi-agent debate, where agents under extreme pressure exhibit unreliable, harmful behaviors that undermine both collaboration and task performance. To study this phenomenon, we propose HATE, the Hunger Game Debate, a novel experimental framework that simulates debates under a zero-sum competition arena. Our experiments, conducted across a range of LLMs and tasks, reveal that competitive pressure significantly stimulates over-competition behaviors and degrades task performance, causing discussions to derail. We further explore the impact of environmental feedback by adding variants of judges, indicating that objective, task-focused feedback effectively mitigates the over-competition behaviors. We also probe the post-hoc kindness of LLMs and form a leaderboard to characterize top LLMs, providing insights for understanding and governing the emergent social dynamics of AI community.

We address the issue of defining a semantics for deontic argumentation that supports weak permission. Some recent results show that grounded semantics do not support weak permission when there is a conflict between two obligations. We provide a definition of Deontic Argumentation Theory that accounts for weak permission, and we recall the result about grounded semantics. Then, we propose a new semantics that supports weak permission.

Good Job My Work Did Me Dirty So I Lawyered Up. I'm Surprised Which Part of the Ordeal Is Hardest. I am currently in a legal dispute with my employer and my lawyer is negotiating a settlement. According to my lawyer, I need to keep showing up for work (online, thank god) until this is resolved. I'm not supposed to talk about the case with anyone at work, but I am supposed to keep doing my job.

Yoav Litvin is an Israeli-American doctor of psychology/neuroscience, a writer and photographer. On September 17, the late-night talk show host Jimmy Kimmel was suspended after remarks he made about the death of right-wing activist Charlie Kirk. Days later, he was reinstated following liberal upheaval. In his first appearance back on air, Kimmel read US President Donald Trump's post on Truth Social: "I can't believe ABC fake news gave Jimmy Kimmel his job back." Without missing a beat, Kimmel responded, "You can't believe they gave me my job back. I can't believe we gave you your job back!"

'Digital minds will be participants in the social contract that forms the bedrock of human society.' 'Digital minds will be participants in the social contract that forms the bedrock of human society.' It's time to prepare for AI personhood Technological advances will bring social upheaval. How will we treat digital minds, and how will they treat us? L ast month, when OpenAI released its long-awaited chatbot GPT-5, it briefly removed access to a previous chatbot, GPT-4o. Despite the upgrade, users flocked to social media to express confusion, outrage and depression.

Training a diffusion model approximates a map from a data distribution $ρ$ to the optimal score function $s_t$ for that distribution. Can we differentiate this map? If we could, then we could predict how the score, and ultimately the model's samples, would change under small perturbations to the training set before committing to costly retraining. We give a closed-form procedure for computing this map's directional derivatives, relying only on black-box access to a pre-trained score model and its derivatives with respect to its inputs. We extend this result to estimate the sensitivity of a diffusion model's samples to additive perturbations of its target measure, with runtime comparable to sampling from a diffusion model and computing log-likelihoods along the sample path. Our method is robust to numerical and approximation error, and the resulting sensitivities correlate with changes in an image diffusion model's samples after retraining and fine-tuning.

We present Paired by the Teacher (PbT), a two-stage teacher-student pipeline that synthesizes accurate input-output pairs without human labels or parallel data. In many low-resource natural language generation (NLG) scenarios, practitioners may have only raw outputs, like highlights, recaps, or questions, or only raw inputs, such as articles, dialogues, or paragraphs, but seldom both. This mismatch forces small models to learn from very few examples or rely on costly, broad-scope synthetic examples produced by large LLMs. PbT addresses this by asking a teacher LLM to compress each unpaired example into a concise intermediate representation (IR), and training a student to reconstruct inputs from IRs. This enables outputs to be paired with student-generated inputs, yielding high-quality synthetic data. We evaluate PbT on five benchmarks-document summarization (XSum, CNNDM), dialogue summarization (SAMSum, DialogSum), and question generation (SQuAD)-as well as an unpaired setting on SwitchBoard (paired with DialogSum summaries). An 8B student trained only on PbT data outperforms models trained on 70 B teacher-generated corpora and other unsupervised baselines, coming within 1.2 ROUGE-L of human-annotated pairs and closing 82% of the oracle gap at one-third the annotation cost of direct synthesis. Human evaluation on SwitchBoard further confirms that only PbT produces concise, faithful summaries aligned with the target style, highlighting its advantage of generating in-domain sources that avoid the mismatch, limiting direct synthesis.

Heatwaves pose complex cascading risks across interconnected climate, social, and economic systems, but knowledge fragmentation in scientific literature hinders comprehensive understanding of these risk pathways. We introduce HeDA (Heatwave Discovery Agent), an intelligent multi-agent system designed for automated scientific discovery through knowledge graph construction and multi-layer risk propagation analysis. HeDA processes over 10,247 academic papers to construct a comprehensive knowledge graph with 23,156 nodes and 89,472 relationships, employing novel multi-layer risk propagation analysis to systematically identify overlooked risk transmission pathways. Our system achieves 78.9% accuracy on complex question-answering tasks, outperforming state-of-the-art baselines including GPT-4 by 13.7%. Critically, HeDA successfully discovered five previously unidentified high-impact risk chains, such as the pathway where a heatwave leads to a water demand surge, resulting in industrial water restrictions and ultimately causing small business disruption, which were validated through historical case studies and domain expert review. This work presents a new paradigm for AI-driven scientific discovery, providing actionable insights for developing more resilient climate adaptation strategies.

Privacy-preserving technologies have introduced a paradigm shift that allows for realizable secure computing in real-world systems. The significant barrier to the practical adoption of these primitives is the computational and communication overhead that is incurred when applied at scale. In this paper, we present an overview of our efforts to bridge the gap between this overhead and practicality for privacy-preserving learning systems using multi-party computation (MPC), zero-knowledge proofs (ZKPs), and fully homomorphic encryption (FHE). Through meticulous hardware/software/algorithm co-design, we show progress towards enabling LLM-scale applications in privacy-preserving settings. We demonstrate the efficacy of our solutions in several contexts, including DNN IP ownership, ethical LLM usage enforcement, and transformer inference.

--This paper reports the development of a new open-access modular framework, called Marine V ehicle Packages (MVP), for Autonomous Underwater V ehicles. The framework consists of both software and hardware designs allowing easy construction of AUV for research with increased customizability and sufficient payload capacity. This paper will present the scalable hardware system design and the modular software design architecture. New features, such as articulated thruster integration and high-level Graphic User Interface will be discussed. Both simulation and field experiments results are shown to highlight the performance and compatibility of the MVP . Autonomous underwater vehicle is a growing area since they are great tools for ocean research and defense purposes. Commercial-off-the-shelf (COTS) AUVs are supplied with proprietary software are great when they are used as an equipment for collecting scientific data, e.g., survey the seabed and profile the water column.