Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2609.13334v1 Announce Type: cross Abstract: Enterprise AI agents often succeed in a demonstration and then stall once they must operate day after day. An industry report estimates that most pil...
arXiv:2609.13443v1 Announce Type: cross Abstract: We demonstrate that training LLMs with RL does not improve performance equally across a dataset. RL shows large improvements on easy problems that an...
arXiv:2609.13512v1 Announce Type: cross Abstract: Federated fine-tuning of large language models with low-rank adaptation reduces per-client trainable parameters, but client-to-server communication r...
arXiv:2609.13889v1 Announce Type: cross Abstract: Harness design has transformed the development of LLM-based agents by integrating memory, tool use, and runtime control. However, this design also in...
Chemical reasoning language models are expected to produce faithful chain-of-thought (CoT) explanations when answering chemistry tasks, but across four model families and twelve tasks, hallucinations are widespread and largely independent of answer correctness. Attribution analyses reveal that these models use a shared scratchpad function: Chem‑R and ether‑0 rely on fragmented SMILES drafts, while ChemDFM‑R emphasizes scaffold, positional, and naming cues. Perturbing Chem‑R’s SMILES sketches degrades generation, indicating that structural drafts can be causally load‑bearing even when verbal structural claims are largely inert.
arXiv:2609.14248v1 Announce Type: cross Abstract: Faithful citation attribution begins with identifying the intended source for a scientific claim. We study this source-identification capability thro...
arXiv:2609.14374v1 Announce Type: cross Abstract: Dynamic trajectory prediction has become an important paradigm for data-driven transient stability analysis (TSA), yet most existing predictors remai...
arXiv:2609.14438v1 Announce Type: cross Abstract: When the same question is asked of multiple AI advisers, as in self-consistency and LLM-as-a-judge panels, Condorcet's jury theorem predicts that add...
arXiv:2609.14211v1 Announce Type: cross Abstract: Scientific applications increasingly rely on high-performance computing (HPC), yet translating a scientist's high-level goal into a correct target-sc...
arXiv:2609.14759v1 Announce Type: cross Abstract: Alignment applied after pretraining is shallow in a measurable way: a single direction in a model's residual stream can be edited out, and the model...
arXiv:2609.14839v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into automated code optimization introduces a critical reliability risk we term the Efficiency Halluc...
arXiv:2609.15100v1 Announce Type: cross Abstract: An image tool can change its underlying generator while retaining its public name, making version attribution from online posts ambiguous. We study t...
arXiv:2609.15544v1 Announce Type: cross Abstract: Enabling human stakeholders to specify reward functions that lead to their desired outcomes is a key challenge in deploying reinforcement learning ag...
arXiv:2609.15606v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress on short video understanding yet remain limited on long videos due to the...
arXiv:2609.15635v1 Announce Type: cross Abstract: A radiology report can already answer a clinical question, so it is hard to tell whether a vision-language model also uses the image. ModaLens, a pai...
arXiv:2609.15659v1 Announce Type: cross Abstract: Native 3D generators turn one image into a single mesh. TRELLIS.2 and its peers deliver high-fidelity non-watertight geometry with materials, but the...
arXiv:2609.15671v1 Announce Type: cross Abstract: Visual Question Answering (VQA) with Vision-Language Models (VLMs) is increasingly used in privacy-sensitive and bandwidth-constrained settings. Fede...
arXiv:2609.15696v1 Announce Type: cross Abstract: Generative AI (GenAI) tools are increasingly woven into how blind and low-vision (BLV) people communicate, not only with digital information, but wit...
arXiv:2609.15939v1 Announce Type: cross Abstract: Language-model agents increasingly operate over complete software repositories, yet cybersecurity evaluations primarily measure whether they can dete...
arXiv:2603.13359v2 Announce Type: replace Abstract: Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusa...