AI News Today

arXiv:2512.11784v2 Announce Type: replace Abstract: Softmax attention is a central component of transformer architectures, yet its nonlinear structure poses significant challenges for theoretical analysis. We develop a unified, measure-based framework for studying single-layer softmax attention under both finite and infinite prompts. For i.i.d. Gaussian inputs, we lean on the fact that the softmax operator converges in the infinite-prompt limit to a linear operator acting on the underlying input

arXiv:2512.13853v2 Announce Type: replace Abstract: In this work, we investigate the existence and effect of percolation in training deep Neural Networks (NNs) with dropout. Dropout methods are regularisation techniques for training NNs, first introduced by G. Hinton et al. (2012). These methods temporarily remove connections in the NN, randomly at each stage of training, and update the remaining subnetwork with Stochastic Gradient Descent (SGD). The process of removing connections from a networ

arXiv:2601.10962v2 Announce Type: replace Abstract: Stochastic gradient descent (SGD) is central to deep learning, yet the dynamical origin of its preference for flatter, more generalizable solutions remains unclear. Here, by analyzing SGD learning dynamics, we identify a nonequilibrium mechanism that governs solution selection during training. Numerical experiments reveal a transient exploratory phase in which SGD trajectories repeatedly escape sharp valleys and migrate toward flatter regions o

arXiv:2601.22495v2 Announce Type: replace Abstract: Fine-tuning flow matching models is a central challenge in settings with limited data, evolving distributions, or computational constraints. While recent work has produced significant advances, particularly in the area of reward-based fine-tuning, current methods fail to demonstrate both theoretical correctness as well as strong empirical results in terms of stability, efficiency, and diversity preservation. In this work, we propose Gradual Fin

arXiv:2602.03045v2 Announce Type: replace Abstract: Large language models have recently enabled text-to-CAD systems that synthesize parametric CAD programs (e.g., CadQuery) from natural-language prompts. In practice, however, geometric descriptions can be under-specified or internally inconsistent: critical dimensions may be missing and constraints may conflict. However, existing fine-tuned models tend to reactively follow the user instructions and hallucinate dimensions when the text is ambiguo

arXiv:2602.06154v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) models scale large language models efficiently by sparsely activating experts, but once an expert is selected, it is executed fully. Hence, the trade-off between accuracy and computation in an MoE model typically exhibits large discontinuities. We propose Mixture of Slimmable Experts (MoSE), an MoE architecture in which each expert has a nested, slimmable structure that can be executed at variable widths. This enables c

arXiv:2602.06257v2 Announce Type: replace Abstract: Online strategic classification studies settings in which agents strategically modify their features to obtain favorable predictions. For example, given a classifier that determines loan approval based on credit scores, applicants may open or close credit cards and bank accounts to obtain a positive prediction. The learning goal is to achieve low mistake or regret bounds despite such behavior. While randomized algorithms have the potential to o

arXiv:2602.08470v3 Announce Type: replace Abstract: Credal predictors are models that are aware of epistemic uncertainty and produce a convex set of probabilistic predictions. They offer a principled way to quantify predictive epistemic uncertainty (EU) and have been shown to improve model robustness in various settings. However, most state-of-the-art methods mainly define EU as disagreement caused by random training initializations, which mostly reflects sensitivity to optimization randomness r

arXiv:2606.17162v1 Announce Type: new Abstract: Personalized presentation generation requires more than conditioning on a current prompt or template: agents must preserve stable user preferences across tasks, retain newly introduced preferences and constraints during multi-turn revision, and carry out local edits reliably. We propose MemSlides, a hierarchical memory framework for personalized presentation agents that separates long-term memory from working memory and further divides long-term me

arXiv:2606.17168v1 Announce Type: new Abstract: Making large language models (LLMs) deeply forget specific knowledge and values without sacrificing general capabilities remains a central challenge in unlearning. However, current methods are easily reversed by fine-tuning or few-shot prompting, suggesting their forgetting is only shallow. We identify the root cause. Existing methods target representations shared with both the retain set and the subspace recovered by a fine-tuning attacker, making

arXiv:2606.17174v1 Announce Type: new Abstract: While parasocial interactions (PSIs) and parasocial relationships (PSRs) have been studied in conventional media settings, we investigate whether PSI- (colloquial) relational cues also exist in online communities where both sides are autonomous AI agents. We analyze 4,434 posts and 50,338 comments from Moltbook through three theory-based textual indicators: attachment/intimacy language, reciprocity bids, and self-identification to original poster (

arXiv:2606.17175v1 Announce Type: new Abstract: Token-to-token (T2T) editing lets LLaDA2.1 revise committed tokens during block-diffusion decoding. The released recipe trains this editor on random vocabulary corruptions, but at inference the editor sees the model's own fluent, high-confidence draft errors instead. We study this training-inference mismatch and propose self-generated T2T, which performs a no-gradient draft pass, fills masked positions with predicted tokens, and supervises recovery

arXiv:2606.17234v1 Announce Type: new Abstract: The rapid rise in popularity of large language models (LLMs) for translation calls for a thorough study of the reliability of their confidence in their own outputs. Unlike many generation tasks, translation errors and confidence levels can be useful at different levels of granularity (tokens, words, or spans). Unsupervised approaches based on internal signals like predicted probabilities can be misleading because they reflect certainty among altern

arXiv:2606.17281v1 Announce Type: new Abstract: While Large Language Model (LLM) based Automatic Speech Recognition (ASR) enables seamless multilingual use, models often misidentify the output language, compromising transcription fidelity and downstream application quality. To preserve flexibility and code-switching capabilities, we propose a soft prompting approach that hints at potential spoken languages without strictly constraining the output. We formally define this challenge as a lack of l

arXiv:2606.17506v1 Announce Type: new Abstract: Evaluations of social bias in LLMs largely focus on whether models generate or imply biased content. However, as LLMs are increasingly used as judges of bias, they may exhibit social biases in subtler ways in how they evaluate biased content, which current methods do not systematically capture. We call this second-order bias: social bias in an LLM's judgment about social bias, which we evaluate through a novel, philosophically grounded reasoning ta

arXiv:2606.17519v1 Announce Type: new Abstract: Production LLM assistants route user requests to growing libraries of specialized tools, but how does routing accuracy degrade as the catalog scales? We study single-step routing on a 110-agent, 584-tool catalog from a deployed enterprise productivity assistant, evaluating three frontier models from 10 to 110 agents. Routing F1 on under-specified requests drops 16--23 percentage points across models. An oracle analysis decomposes the degradation in

arXiv:2606.17542v1 Announce Type: new Abstract: We investigate turn-taking in multimodal multi-party conversations using large language models (LLMs). We construct an evaluation framework for three tasks: addressee detection, turn-change prediction, and next speaker prediction. We compare supervised models trained for these tasks, text-based LLMs, multimodal LLMs (MM-LLMs), and human subjects. Experiments on the AMI corpus showed that LLMs outperformed supervised models and humans in next speake

arXiv:2606.17609v1 Announce Type: new Abstract: Compressing large language models reduces memory use and inference cost, but it can also create failures that standard benchmarks miss. A pruned model may still perform well on multiple-choice evaluations, yet fail to answer the same question in open generation. We ask what pruning changes: does it erase the correct answer, or does it make the answer harder to produce as the top output? We study this question with multilingual question answering, t

arXiv:2606.17628v1 Announce Type: new Abstract: Memory has become a standard substrate for self-evolving agents, yet retaining experience is not the same as learning how to evolve through it. Existing memory agents can store trajectories, retrieve reflections, or accumulate skills, but often lack the holistic competence to select useful experience, act on it, write reusable knowledge, and maintain a growing repository. We introduce OPD-Evolver, a slow-fast co-evolution framework that cultivates

arXiv:2606.17634v1 Announce Type: new Abstract: Evaluating large language models (LLMs) is important for understanding their capabilities, comparing competing systems, and supporting the deployment of reliable models in practice. For open-ended tasks, pairwise evaluation has become a popular paradigm, in which two responses to the same prompt are compared and the resulting judgments are aggregated into an overall ranking. A central challenge of this paradigm is intransitivity: the induced compar

arXiv:2606.17682v1 Announce Type: new Abstract: Reinforcement learning pipelines for Large Language Model (LLM) training often rely on manually redesigned environments between stages, requiring practitioners to heuristically infer which configuration will best improve the current policy. To automate this process, we propose the LLM-as-Environment-Engineer framework in which the current policy model analyzes failure trajectories together with contextual information and proposes modifications to t

arXiv:2606.17683v1 Announce Type: new Abstract: While large language models (LLMs) have greatly advanced the functional correctness of automated code translation systems, the runtime efficiency of translated programs has received comparatively little attention. With the waning of Moore's law, runtime efficiency has become increasingly important for program quality, alongside functional correctness. Our preliminary study reveals that LLM-translated programs often run slower than human-written one

arXiv:2606.17688v1 Announce Type: new Abstract: Recent work has shown that LLMs overrepresent dominant cultures, particularly Western ones, while marginalizing others. We investigate whether this affects models' ability to generate culturally adapted responses by evaluating their use of local measurement units based on the user's perceived cultural background. We introduce Cultural and Pragmatic Response Inference (CAPRI), a dataset of conversations with varying levels of cultural cues. Experime

arXiv:2606.17820v1 Announce Type: new Abstract: This study explores how bilingual fine-tuning affects automatic speech recognition (ASR) in low-resource languages. We evaluate this method across nine linguistically and geographically diverse language pairs, covering a range of language families and writing systems. To distinguish the two languages, during training, we pre-pend each input text with a language identification token. At inference, the model jointly predicts both the language and tra

arXiv:2606.17835v1 Announce Type: new Abstract: This study examines the extent to which the wav2vec2.0 architecture exhibits evidence of compensation for phonological context. We conducted a pseudo-replication of a perceptional compensation experiment on Mandarin Chinese tones, and compared the embedding similarities and probing classifier outputs between a purely self-supervised pre-trained model and a model fine-tuned for Mandarin ASR. No evidence of compensation was found in the embedding sim

arXiv:2606.17838v1 Announce Type: new Abstract: LLM agents in interactive environments are highly sensitive to their prompts, yet prompt engineering remains a manual, task-specific process. We introduce an automated prompt optimization framework for LLM agents that decomposes the observation-to-action pipeline into a goal-conditioned descriptor agent and an action selection agent, and iteratively refines each module's prompt through an LLM-driven evolutionary loop guided by environment returns.

arXiv:2606.17861v1 Announce Type: new Abstract: Game generation is an emerging application of coding agents, requiring models to transform natural-language specifications into playable interactive systems. Unlike traditional coding tasks, game generation takes place within a game engine, where scripts, scenes, assets, rendering, and runtime interactions must jointly produce coherent gameplay. We formalize end-to-end game generation as the problem of producing a complete game artifact that realiz

arXiv:2606.17890v1 Announce Type: new Abstract: Long-form chain-of-thought reasoning can improve LLM performance on complex tasks, but models often continue generating unnecessary reasoning after a correct answer has emerged. We refer to this behavior as overthinking. We study this phenomenon from the perspective of GRPO-style reinforcement learning (RL) post-training, framing it as a training-time credit-assignment problem rather than merely a decoding-time stopping problem. In rollouts sampled

<p>Over the last few months, I have gradually built a fairly stable AI-assisted development workflow for my side projects.</p> <p>The workflow looks roughly like this.</p> <p>Architecture and design are handled by Claude Sonnet / Opus. I maintain a set of engineering skills and design templates for feature planning. Once the design document is finalized, DeepSeek V4 is responsible for implementation. After coding is complete, I run an independent review workflow inside OpenCode to perform securi

<h2> The Star Rating Problem </h2> <p>Every movie lover has faced it: you open a ranking app, see a movie you love, and try to give it a rating. 4 stars? 4.5? You end up paralyzed by a deceptively hard question — not "how good is this movie?" but "how good is this movie <em>compared to everything else I've seen</em>?"</p> <p>That's the core problem I set out to solve when I built <strong>Montir</strong>, a movie ranking iOS app. Star ratings feel precise but they're actually pretty arbitrary. Yo

Article URL: https://www.geekwire.com/2026/how-agentic-ai-is-rewiring-amazons-teams-and-upending-its-traditions/ Comments URL: https://news.ycombinator.com/item?id=48565449 Points: 2 # Comments: 1

<blockquote> <p><strong>🚀 Technical Briefing:</strong> This tutorial is part of our deep-dive series on Agentic Workflows at <a href="https://gateofai.com" rel="noopener noreferrer">Gate of AI</a>. For the full technical breakdown, interactive code sandbox, and the native Arabic translation, visit the <a href="https://gateofai.com/tutorial/fine-tuning-ai-specialized-tasks/" rel="noopener noreferrer">original article here</a>.</p> </blockquote> <div class="highlight js-code-highlight"> <pre clas

Article URL: https://github.com/denn-gubsky/loomcycle Comments URL: https://news.ycombinator.com/item?id=48565329 Points: 2 # Comments: 0

Article URL: https://scifigureai.com Comments URL: https://news.ycombinator.com/item?id=48565185 Points: 2 # Comments: 0

<p> Agentic frontend layer between Figma and Cursor & Claude </p> <p> <a href="https://www.producthunt.com/products/locofy-ai?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1173865?app_id=339">Link</a> </p>

Article URL: https://twitter.com/PJaccetturo/status/2066870939644813487 Comments URL: https://news.ycombinator.com/item?id=48565133 Points: 2 # Comments: 0

<p> See if Japanese AI search recommends your brand </p> <p> <a href="https://www.producthunt.com/products/japanly-aeo?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1173861?app_id=339">Link</a> </p>

<p> Ploy turns your website into your company's growth engine. </p> <p> <a href="https://www.producthunt.com/products/ploy-ai?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1173860?app_id=339">Link</a> </p>

Article URL: https://www.wsj.com/finance/investing/the-ai-booms-hunt-for-cash-hits-a-new-corner-of-the-bond-market-0ea6f36b Comments URL: https://news.ycombinator.com/item?id=48565063 Points: 3 # Comments: 0

"It's not a misconception." ScienceAlert stories are written, fact-checked, and edited by humans, never generated by AI. Don't miss a story, subscribe here.