ARISE giới thiệu kiến trúc bộ nhớ tự‑tiến hóa cho các enterprise LLM agents, cho phép chúng tự sửa lỗi mà không cần cập nhật mô hình hoặc workflow.
⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5459, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.22971v1 Announce Type: new Abstract: Safety benchmarks for computer-use agents (CUAs) place the harm either in the intent of the task or on a single screen: a malicious instruction, an injected command, a phishing page. An agent that checks the task and each screen in…
arXiv:2611.20389v1 Announce Type: new Abstract: Execution traces help diagnose AI-agent failures, but sharing them can expose customer identities. For example, detecting that an agent handled the wrong customer's records requires knowing whether the records belong to the request…
arXiv:2611.21936v1 Announce Type: new Abstract: Traditional malware classification methods struggle to keep pace with rapidly evolving threats. Image-based malware classification offers a promising alternative by converting malware binaries into grayscale images for analysis wit…
arXiv:2611.23715v1 Announce Type: new Abstract: Compiler rewrites can preserve returned values while violating object lifetime or ownership. Such failures arise when a rewrite changes when an object remains live, whether a borrowed pointer stays supported, or what ownership reac…
arXiv:2611.15097v1 Announce Type: new Abstract: Web agents need to use private context without unnecessarily disclosing it. Effective protection must distinguish between requests that may be sent after sanitization and those that must be withheld, while preserving the informatio…
Coding agents can synthesize and optimize code-based policies from simulator feedback, allowing the resulting program to act with zero inference model calls. But for long horizon tasks, two challenges arise: local improvements can hurt final success and switching to a new objecti…
arXiv:2611.14984v1 Announce Type: new Abstract: Reward models (RMs) are increasingly deployed as service components in LLM alignment pipelines, where payment, audit, moderation, and governance workflows act on the scores they return. An inference proof alone does not show whethe…
arXiv:2611.21946v1 Announce Type: new Abstract: A reasoning model that has reached a correct answer can lose it by continuing to think. Deciding whether to stop means comparing two probabilities at the same point of a chain: that the answer the model would give if stopped now is…
arXiv:2611.21998v1 Announce Type: new Abstract: Personal assistants accumulate months of conversations, but today's long-term memory stacks put derivation or selection between a question and its evidence. In a system-level comparison on LongMemEval, two commercial assistants sco…
arXiv:2611.22219v1 Announce Type: new Abstract: Background: Generative large language models (LLMs) offer an alternative to encoder-based clinical named entity recognition (NER), but their performance on fine-grained Japanese extraction tasks and sensitivity to generation settin…
arXiv:2611.21694v1 Announce Type: cross Abstract: Transmitting an electrocardiogram (ECG) waveform can expose demographic information beyond an intended diagnostic task. We evaluate TIBECG, an architectural temporal information bottleneck, on individual leads extracted from hosp…
arXiv:2611.19064v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become an important approach to improving the reasoning capabilities of large language models. In tasks such as code generation and instruction following, multiple verifiers…
arXiv:2611.18910v1 Announce Type: new Abstract: Memory safety rules out classical code reuse attacks that rely on arbitrary memory corruption, but does not eliminate code reuse altogether. Attacks such as object injection, prototype pollution, class pollution, DOM clobbering, an…
arXiv:2611.20498v1 Announce Type: new Abstract: As new attack categories emerge, network intrusion detection models need to be updated; however, when fine-tuned sequentially on new classes, previous classes are forgotten, resulting in catastrophic for- getting. The three public …
arXiv:2611.17583v1 Announce Type: new Abstract: A representation that retains one bit about a four-state world can solve a task perfectly, while another that retains 1.5 bits on average reaches only 75% accuracy. The difference lies in which distinctions each representation pres…
arXiv:2611.17763v1 Announce Type: new Abstract: When a language model accepts a false correction in a factual discussion, its next answer can depend on how the conversation continues. We introduce Knowledge Answer Divergence (KAD), an event-conditioned evaluation protocol that d…
Underwater image enhancement is challenging to evaluate due to the lack of clean reference images, so researchers rely on no-reference image quality assessment (NR-IQA) metrics. However, it remains unclear whether these metrics agree with human judgments. We evaluate 73 handcraft…
arXiv:2611.14769v1 Announce Type: new Abstract: Arena-style rankings of language models are a widely used evaluation framework in online leaderboards, research papers, and model evaluation in production. These rankings aim to realistically assess model performance using pairwise…
arXiv:2611.16818v1 Announce Type: new Abstract: Private decision-tree evaluation lets a server classify a client's encrypted query without learning the input. In the non-interactive, path-based setting over TFHE, the server returns a single encrypted prediction by aggregating pe…