Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2609.15309v1 Announce Type: new Abstract: Large language model (LLM) agents allocate test-time compute adaptively as they revise solutions, use tools, explore alternatives, and decide when to s...
arXiv:2609.15684v1 Announce Type: new Abstract: Language agents increasingly rely on reusable skills, but post-failure repair is often handled by opaque one-shot reflection: a model generates a skill...
ZGCM-1 is a 7B dense foundation model trained from scratch with extreme data, system, and algorithmic efficiency. It uses a core premise that compact models can overcome capacity limits by combining deliberate internal thinking with active external tool use, supported by a 256K context and an end‑to‑end high‑efficiency training recipe that includes interleaved gated sliding‑window and full attention, a stable FP8 Muon optimizer, progressive curriculum scaling, and reformulation of interaction traces into Markov Decision Processes. The model is competitive with much larger frontier models on challenging mathematical reasoning and agentic search tasks, offers a ~4.2× efficiency improvement in pre‑training time‑to‑loss, and its weights, checkpoints, training code, data recipes, and logs are fully open‑source to support community research.
arXiv:2512.09944v4 Announce Type: replace Abstract: Echocardiography interpretation requires integrating multi-view temporal evidence with quantitative measurements and guideline-grounded reasoning,...
NoteVQA is a new benchmark that collects 252 real‑life visual questions from the Chinese image‑sharing platform Xiaohongshu, covering 12 topics and 7 user intents. Each question is paired with a concise expert reference and a human‑audited interleaved answer that blends text and visual evidence. The study evaluates VLMs on short‑answer correctness and interleaved answer quality using a new AgenticInterleave framework and a 12‑dimensional IVR‑12 rubric, finding that even state‑of‑the‑art models achieve only about 53% accuracy and lag behind human references in content quality.
The paper evaluates eleven vision‑language models (VLMs) for extracting structured fields from business documents, focusing on robustness, cost, and governance rather than just accuracy. Using a held‑out set of 750 synthetic checks, the study finds that fine‑tuning open‑source VLMs on 3,000 samples yields an F1 score above 0.98, surpassing all zero‑shot commercial systems, while GPT‑5 tops the commercial group and Claude Sonnet 4.5 fails on date extraction. The authors also present a practitioner‑oriented selection framework that maps task profiles—such as quality, latency, governance, and volume—to recommended approaches via filtering and total‑cost minimization, demonstrated on a mid‑volume document‑extraction scenario.
arXiv:2609.14758v1 Announce Type: cross Abstract: Tool-augmented language models are evaluated on whether they reach the right answer, not on whether they report honestly when a tool fails to supply...
arXiv:2609.14783v1 Announce Type: cross Abstract: Robots need touch to manipulate objects safely and reliably, as many properties, such as softness, texture, and contact stability, are hard to infer...
arXiv:2609.15408v1 Announce Type: cross Abstract: Long-video understanding remains challenging for multimodal large language models (MLLMs) because densely encoding long frame sequences is computatio...
arXiv:2404.00727v3 Announce Type: replace Abstract: All state-of-the-art coreference resolution (CR) models involve finetuning a pretrained language model. Whether the superior performance of one CR...
arXiv:2601.19847v3 Announce Type: replace Abstract: Despite the strong reasoning capabilities of recent large language models (LLMs), achieving reliable performance on challenging tasks often require...
arXiv:2602.00377v3 Announce Type: replace Abstract: Existing knowledge probing methods rely on pre-defined queries, limiting extraction to known concepts. We introduce DecompressionLM, a stateless fr...
arXiv:2603.29396v2 Announce Type: replace Abstract: Standard evaluations of Large language models (LLMs) focus on task performance, offering limited insight into whether correct behavior reflects app...
arXiv:2512.24565v4 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly serving as autonomous agents, and their utilization of external tools via the Model Context Protocol...
arXiv:2606.27314v2 Announce Type: replace Abstract: To avoid moderation and surveillance on social media, some users routinely invent indirect linguistic expressions (ILE) that camouflage sensitive m...
arXiv:2607.29397v3 Announce Type: replace Abstract: Deploying large language models in realistic server environments poses challenges, as the system needs to provide high-quality responses with low l...
arXiv:2609.07093v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) enables large language models (LLMs) to answer questions by accessing external knowledge and has been widely a...
arXiv:2407.02395v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used for program synthesis, yet they often generate code that is functionally plausible but ins...
arXiv:2606.00684v3 Announce Type: replace-cross Abstract: We address the problem of out-of-distribution (OOD) detection for target observations embedded in a subspace of the high dimensional data spa...
arXiv:2606.17467v3 Announce Type: replace-cross Abstract: Prompt injection defenses evaluated on synthetic benchmarks do not generalize to real enterprise documents, which are longer, denser, and int...