cập nhật 2 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5479, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

26
M-Plan: Comprehensive Planning For LLM Agents with Memory Arrangement
📄 Paper arXiv cs.AI 28 ngày trước

arXiv:2610.27032v1 Announce Type: new Abstract: Large language model (LLM)-based agents have recently demonstrated outstanding performance in single-turn tasks, yet they continue to struggle with long-horizon tasks, particularly in environments without prior training. A key limi…

🅲 hạng C
26
PROVISO: Provenance-Informed Action Selection for Secure LLM Agents
📄 Paper arXiv cs.AI 28 ngày trước

arXiv:2610.27115v1 Announce Type: new Abstract: LLM agents act on the external world through tools and third-party skills, so a single executed action can cause irreversible harm. Existing defenses judge a proposed action without tracking whether its content comes from the user …

🅲 hạng C
26
PORA: Learning When More Reasoning Pays Off for LLM Agents
📄 Paper arXiv cs.AI 28 ngày trước

arXiv:2610.27119v1 Announce Type: new Abstract: LLM agents perform tasks over multiple steps and revise their actions based on feedback. As the total reasoning budget is often limited and must support future steps, the agent must choose between short and long reasoning before ea…

🅲 hạng C
26
Vulnerability Analysis for Safe Multi-Agent Reinforcement
📄 Paper arXiv cs.AI 28 ngày trước

arXiv:2610.27293v1 Announce Type: new Abstract: Safe Multi-Agent Reinforcement Learning (SMARL) aims to learn cooperative control policies under prescribed safety constraints. Al- though existing SMARL methods focus on enforcing safety during policy optimization, their vulnerabi…

🅲 hạng C
26
Self-Improving Agents with World Model Predictive Paths
📄 Paper arXiv cs.AI 27 ngày trước

arXiv:2610.28945v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly expected to interact with environments and improve their decisions during deployment. However, how anticipating future outcomes and drawing on accumulated interaction experience ca…

🅲 hạng C
26
PerMIT: Securing Persistent Memory for LLM Agents via Machine-Checked Integrity Theorems and Scalable Community Trust
📄 Paper arXiv cs.AI 27 ngày trước

arXiv:2610.28987v1 Announce Type: new Abstract: Persistent memory is a largely undefended surface for injection and poisoning, and the same risk limits memory sharing among agents. We present PerMIT, a memory architecture with provable integrity guarantees under an explicit trus…

🅲 hạng C
26
LLM-Based Exogenous World Modeling for Dynamic Scheduling
📄 Paper arXiv cs.AI 27 ngày trước

arXiv:2610.29308v1 Announce Type: new Abstract: Dynamic scheduling requires dispatching online arrivals while anticipating future jobs, as poor decisions can compound downstream costs under nonlinear tardiness objectives. We show that a pretrained large language model (LLM) can …

🅲 hạng C
26
Correlated Failures of AI Approval Monitors
📄 Paper arXiv cs.CR 27 ngày trước

arXiv:2610.29178v1 Announce Type: new Abstract: Before an AI agent takes a consequential action, such as paying, messaging or changing code, several monitors check it. Their verdicts are combined by aggregating scores or by counting approvals, whatever inputs the monitors share.…

🅲 hạng C
26
Better Reasoning, Not Just Bigger Models: A Structure-Grounded Framework for Efficient and Reliable Inference
📄 Paper arXiv cs.AI 26 ngày trước

arXiv:2610.30611v1 Announce Type: new Abstract: Scaling large language models has substantially improved linguistic fluency, yet reliable autonomous agents require more than fluent generation. In multi-turn inference, current agentic systems often produce semantically plausible …

🅲 hạng C
26
Self-Evolving Static Analysis via LLM Pseudo-Labeling
📄 Paper arXiv cs.CR 26 ngày trước

arXiv:2610.30184v1 Announce Type: new Abstract: Security bugs often slip past static analysis not because they are impossible to detect, but because detection rules have not yet been written for the code in front of us. New frameworks, APIs, and coding idioms continually create …

🅲 hạng C
26
RSI-Opt: Recursive Self-Improvement Optimizer Agents For Model Training
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.32026v1 Announce Type: new Abstract: Conventional neural-network training typically follows a predefined optimization recipe, motivating a LLM agent that monitors training dynamics and adjusts optimizer settings as training progresses, but a fixed agent policy does no…

🅲 hạng C
26
Understanding Communication Failures in Multi-Agent LLM Systems
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.32060v1 Announce Type: new Abstract: Multi-agent LLM systems aim to improve reasoning through debate, evidence sharing, and mutual correction, but interaction can also introduce failures that final accuracy alone cannot explain. Agents may converge too early, ignore d…

🅲 hạng C
26
PersonaScienceBench: Evaluating Scientific Agents with Diverse Simulated Researchers
📄 Paper arXiv cs.AI 23 ngày trước

arXiv:2610.32106v1 Announce Type: new Abstract: Scientific agents collaborate with researchers whose expertise and preferences differ, but benchmarks usually hold the collaborator fixed. We introduce PersonaScienceBench: 200 tasks from five benchmarks across four scientific doma…

🅲 hạng C
26
A Deterministic Security Runtime for LLM Agents on MPI and Batch-Scheduled HPC Systems: Consensus-Governed, Hardware-Rooted Supervision of Every Rank
📄 Paper arXiv cs.CR 22 ngày trước

arXiv:2610.33318v1 Announce Type: new Abstract: Large language model agents launch simulations on high-performance computing (HPC) systems, where one sbatch or mpirun can commit thousands of node-hours and a forged result can cost lives. Of 23 surveyed systems, none supervises t…

🅲 hạng C
26
Ring-0 by Default: Agents as Operating Systems (AaOS)
📄 Paper arXiv cs.CR 22 ngày trước

arXiv:2610.33753v1 Announce Type: new Abstract: LLM agents now read and write files, start processes and subagents, fetch network content, load third-party extensions, and save and resume state, which are the responsibilities of an operating system. They gained these functions w…

🅲 hạng C
26
SentryBench: A Cost-Sensitive Benchmark for Adversarial Robustness of Tool-Using LLM Agents in Public-Safety Deployments
📄 Paper arXiv cs.CR 22 ngày trước

arXiv:2610.34535v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly wired to consequential tools that send public alerts, dispatch responders, and query citizen records, where one erroneous tool call carries real-world cost. Existing agent-safety b…

🅲 hạng C
26
AOS-Bench: Can LLM Agents Manage Dynamic Workloads?
📄 Paper arXiv cs.AI 22 ngày trước

arXiv:2610.33178v2 Announce Type: new Abstract: Coding agents are moving from handling one request at a time to serving as persistent assistants to which users hand a stream of work: a build, a data-processing job and a bug fix may all be pending on the same machine at once. Suc…

🅲 hạng C
26
Estimation of Propagated Risk in LLM-based Multi-Agent Systems
📄 Paper arXiv cs.AI 22 ngày trước

arXiv:2610.33282v1 Announce Type: new Abstract: Large Language Model (LLM) based multi-agent systems introduce a distinctive reliability challenge in which actions taken by upstream agents can affect the correctness of downstream agents. While prior work has investigated error p…

🅲 hạng C