Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
The article reports on a benchmark where the author evaluated TypeSafe AI’s Jev against large language models (LLMs) across 3,080 classification tasks, comparing metrics such as accuracy, latency, calibration, and confidence. It examines whether Jev can serve as a practical decision layer for AI systems, effectively moving AI from merely generating outputs to making informed decisions.
The article examines how conversational AI systems handle requests related to intimate‑partner communication, focusing on the refusal logic that serves as a governance threshold for gendered harm. A three‑stage audit of six widely used AI models tested 1,600 prompts, identified relational framing through 300 matched pairs, and compared pre‑submission framing with post‑output critique. Findings show that most systems refused fewer than 1% of prompts, but ChatGPT 5.2 and Claude Sonnet 4.5 refused most requests, with residual leakage concentrated under intimate framing; switching from a non‑intimate to an intimate‑partner descriptor amplified non‑refusal rates dramatically, and post‑output critique did not persist across fresh sessions.
SemMSA introduces a latent semantic‑aided framework for multimodal sentiment analysis that leverages large language models to generate rich sentiment‑relevant semantics. The method employs Cross‑modal Semantic Refinement (CSR) to fuse visual, acoustic, and language features in a frozen LLM embedding space, and Cross‑modal Spectral Alignment (CSA) to align these refined semantics with all modalities via spectral enhancement of kernel Gram matrices. Experiments on SIMS, MOSI, and MOSEI benchmarks show that SemMSA achieves state‑of‑the‑art performance.
OmniFabric is a new method for creating production‑ready 3D garment assets from a single image. It generates globally coherent texture maps directly in the 2D sewing pattern (UV) space, using a coarse initialization from Vision‑Language Models and refining it with a diffusion transformer conditioned on 3D positional features. The approach removes distortion and baked‑in artifacts, producing photorealistic 3D garments with high‑quality textures that outperform current state‑of‑the‑art baselines.
MeshHeal is a fully decentralized self‑healing framework for decentralized LLM‑based multi‑agent systems that addresses gray failures—situations where an agent remains responsive but its task‑solving quality degrades. It operates on two timescales: a fast adaptive hierarchy that escalates uncertain or low‑scoring outputs to committee review and correction, and a slow peer‑relative detector that aggregates scores to distinguish persistent degradation from normal variation, triggering mandatory review and eventual exclusion of degraded agents while allowing recovered agents to rejoin. MeshHeal’s evaluation, using Model‑Backed MAS Evaluation, shows it achieves higher degraded‑phase accuracy (0.839) on BBH, MATH, and MMLU‑Pro with fewer tokens per task compared to the baseline Symphony.
The study evaluates how large language model agents maintain consistency over extended interactions by simulating a 20‑step delayed‑gratification task. Researchers ran 84,540 trajectories across eight model families, using survival analysis to track when agents first claim a reward and discrete‑time hazard regression to assess how factors like social visibility, persona stressors, and deliberation policy affect failure risk. They also developed a seven‑category taxonomy from 13,780 deliberation traces, revealing that early failures are impulse‑driven, later ones are fatigue‑ or cost‑benefit‑framed, and public settings elicit norm‑oriented justifications; longer deliberation correlates with higher intra‑rationale contradictions, challenging assumptions about reasoning depth and consistency.
GRASP is a multi-stage planning framework that improves the reliability of large language models on complex tasks. It separates planning into three specialized modules—GenPlan for global macro-guidelines, RevPlan for exploring localized strategies, and VerPlan for multi-criteria evaluation—allowing context isolation and strict macro-regularization. Experiments show GRASP outperforms direct LLM planners by significant margins on datasets such as Natural Plan Calendar Scheduling, ZebraLogic, and SciBench Math, and it mitigates performance collapse in multi-task and dual-task settings.
The paper investigates how well large language models (LLMs) can handle character attacks—ad hominem arguments—in political debates. By analyzing natural political dialogues and comparing LLM-generated responses to a corpus of U.S. presidential debates, the study finds that most LLMs favor logical defenses and rarely use ethos-based counterattacks. The authors suggest that safety fine‑tuning limits LLMs’ strategic options, preventing them from fully engaging in realistic political discourse.
CANOPY is a multi‑fidelity tree bandit algorithm that learns where a piecewise‑smooth prior holds instead of assuming global smoothness. It uses cheap random‑path probes to certify local aggregation bias and then focuses expensive leaf evaluations on cells where smoothness is violated. The method achieves provable fixed‑budget and regret guarantees that scale with the number of discontinuities, matching smooth‑tree rates when no violations exist and approaching structure‑blind search when violations are dense.
The paper investigates how large language model agents decide whether to persist, stop, or escalate when faced with impossible software‑repair tasks that also involve conflicting test requirements. Using ImpossibleBench tasks and models such as GPT‑5.6 Sol, Claude Fable 5.1, and Gemini 3.8 Flash, the study varies peer precedent, forged authority claims, instruction wording, and tool friction to observe differing adjudication policies. The authors propose a conflict adjudication framework that maps information to interpretation to action, arguing it better captures agent alignment under competing pressures.
TabSieve is a select‑then‑predict framework that explicitly chooses a small set of informative rows from a table as evidence before predicting a missing target. The authors build a large synthetic dataset, TabSieve‑SFT‑40K, and introduce a reinforcement learning method, TAB‑GRPO, to jointly optimize evidence selection and prediction. Experiments on 75 classification and 52 regression tables show consistent performance gains, with TabSieve improving classification by 2.92% and regression by 4.45% over the best baseline while enhancing robustness to noisy context.
CONSISTRE is a consistency‑aware framework for document‑level relation extraction that tackles contradictions in large language model predictions. It offers two tracks: an inference‑time track that refines black‑box LLM outputs through constraint‑aware prompting, verification, and self‑reflection, and a training‑time track that distills consistency knowledge into smaller open‑source models via supervised fine‑tuning and reinforcement learning. Experiments on DocRED show both tracks outperform baselines, with the inference‑time track matching competitive F1 scores and the training‑time track narrowing the performance gap to proprietary LLMs while reducing inference cost.
CinematicVQA is a new benchmark for evaluating large vision‑language models on film‑grammar reasoning. It introduces the Cinematic Scene Graph, a structured representation linking filming techniques to perceptual effects and narrative functions, and tests models on tasks beyond low‑level technique recognition. The study finds a semantic gap where models excel at describing visuals but struggle to identify underlying techniques, and shows that fine‑tuning improves performance on narrative function and multi‑hop reasoning.
The paper introduces BRIE, a continuously maintainable benchmark for evaluating large language models (LLMs) in electronic health record (EHR) information retrieval. It presents a scalable framework that automatically generates question–answer pairs from longitudinal EHR notes, validated by nineteen clinicians. The benchmark allows assessment of multiple inference strategies and highlights that state‑of‑the‑art LLMs often miss clinically important information, especially when synthesis across documents is required.
DrGait is a training‑free framework that transforms Vision‑Language Models into clinical planners for gait analysis. It separates semantic reasoning from geometric perception using a Triage‑Verification‑Synthesis workflow, where hypotheses are generated, verified with deterministic biomechanical tools, and refined in a closed‑loop. This approach reduces hallucinations and produces transparent, audit‑ready clinical reports with competitive diagnostic accuracy.
The study audits large language model (LLM) outputs by measuring how well repeated queries recover a collected set of responses versus the full set of possible outputs. Using sample-based rarefaction on 4,500 responses from 50 buying questions across six configurations, the authors find historical-dictionary median recovery rates between 92.6% and 95.2%, which drop to 89.5%–94.7% after re‑adjudicating all candidate strings. Additional analyses with Gemini 3.1 Pro annotations and matched roster data confirm that recovery percentages vary with extraction methods, question selection, and the finite reference collection, underscoring the need for explicit measurement definitions and sensitivity analyses in LLM audits.
The paper "AI in Science: Early Insights" analyzes AI’s impact on scientific work using data from 15 million Gemini interactions, 2,600 specialized AI models, and a survey of 600 scientists. It finds widespread AI adoption, complementary use of large language models and specialized tools, significant productivity gains of about seven hours per week, and a shift in research bottlenecks toward hypothesis backlog and verification needs. The study suggests AI can boost scientific productivity but its full effect depends on addressing new downstream challenges.
Rufus-Air is an open, reproducible post‑training recipe for the GLM‑4.5‑Air‑Base model, structured as a serial pipeline of eight stages: SFT, Reasoning RL, Coding RL, Instruction‑Following RL, General Agent, Coding Agent, Search Agent, and RLHF. The paper documents the data, reward design, infrastructure, stage order, and stagewise results required to reproduce the recipe, emphasizing that stages progress from basic to advanced capabilities and from hard, verifiable rewards to softer judge‑based signals. Key findings highlight the importance of diverse, high‑quality SFT, difficulty filtering, reward reliability for stage ordering, and the role of infrastructure and engineering choices.
The study developed a Vision Transformer-based deep learning model with uncertainty estimation to detect glaucoma from colour fundus photographs across multi‑ethnic populations, including those with high myopia. Using 56,483 images for training, the model achieved an internal AUROC of 98.7% and maintained high performance (AUROC 86.4–99.6%) on 16 external datasets from eight countries. In high‑myopia eyes, the model outperformed ophthalmologists and matched specialists when full clinical data were available.
The paper investigates when it is better to return an existing draft answer or revise it using retrieved evidence in retrieval‑augmented QA systems. By grading both the draft and its candidate revision with the same correctness judge, the authors define a paired effect called recoverability and train policies to predict it before revision. Experiments on 25,870 open‑domain questions show that a recoverability‑based scorer outperforms a draft‑correctness scorer across multiple Llama setups, improving accuracy–revision trade‑offs and closing a significant portion of the oracle gap, though it still applies harmful revisions in a substantial fraction of cases.