cập nhật 7 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5448, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

31
Weighing the Envelope: Component Weight and Arbitration in Envelope-Layer Defenses for a Single LLM Agent
📄 Paper arXiv cs.CR 11 giờ trước

Bài nghiên cứu mới giới thiệu mô hình Envelope Layer cho LLM Agent, đánh giá trọng lượng các thành phần và cách giải quyết rủi ro khi công cụ MCP và bộ nhớ lâu dài đồng thời tồn tại. Điều này giúp cải thiện an toàn và giảm rủi ro lây nhiễm nội dung độc hại trong AI Agent.

🅲 hạng C
30
Metrics-in-the-Loop: Complexity Feedback Reshapes Agent-Written Code
📄 Paper arXiv cs.AI 11 giờ trước

arXiv:2611.23817v1 Announce Type: new Abstract: Coding agents now write whole codebases in long autonomous runs, guided mainly by whether their tests pass. Yet passing tests alone does not reveal accumulating complexity or gaps in test coverage, which then persist as agents exte…

🅲 hạng C
28
GRAFT: Execution-Guided Genetic Recombination for Agent Design
📄 Paper arXiv cs.AI 11 giờ trước

arXiv:2611.23509v1 Announce Type: new Abstract: Automated agent design searches for executable architectures that improve LLM-based agent performance, with evolutionary methods using language-model crossover to recombine promising mechanisms for task decomposition, model coordin…

🅲 hạng C
28
Auditable Clinical Support with Decision Agents
📄 Paper arXiv cs.AI 11 giờ trước

arXiv:2611.23700v1 Announce Type: new Abstract: Clinicians reviewing a diagnostic work-up will ask what was considered at each step and why the assessment changed. Agents powered by free text can reach physician-level diagnostic accuracy, but their written reasoning does not alw…

🅲 hạng C
28
Continual Tool-Space Extension Learning for Multimodal Agents
📄 Paper arXiv cs.AI 11 giờ trước

arXiv:2611.23810v1 Announce Type: new Abstract: Multimodal agents largely rely on generic tools such as cropping, search, and code execution, leaving specialist vision models outside their tool space. However, bringing such a model into an already trained agent is not straightfo…

🅲 hạng C
26
GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance
📄 Paper arXiv cs.AI 11 giờ trước

arXiv:2611.23476v1 Announce Type: new Abstract: Autonomous AI agents pair a frozen base model with an editable harness of prompts, skills, tool rules, and memory. Recursive self-improvement (RSI) adapts this harness from experience without weight updates, yet self-editing withou…

🅲 hạng C
26
Modeling LLM Reasoning Dynamics with Structural Representations
📄 Paper arXiv cs.AI 11 giờ trước

arXiv:2611.23749v1 Announce Type: new Abstract: Language-model reasoning alternates between sustained activities and local operations. We study how this temporal structure predicts continuation and the computation needed to analyze it. T/E/S combines text, local events, and span…

🅲 hạng C
26
Intent Contracts: Taking Tools Away from Agents
📄 Paper arXiv cs.CR 11 giờ trước

arXiv:2611.24025v1 Announce Type: new Abstract: Intent contracts are an authorization interface for tool-using LLM agents in which the planning model holds no tools. For each step it submits a short logged contract: a goal, a verbatim quotation of the user, and scope fields. Cod…

🅲 hạng C
26
When Shuffling Fails: Token Recovery from Obfuscated KV Caches
📄 Paper arXiv cs.CR 11 giờ trước

arXiv:2611.24276v1 Announce Type: new Abstract: LLM serving systems store, offload, and share KV caches, exposing token-level representations to infrastructure operators and co-tenants. Shuffled obfuscation combines secret linear transforms with fresh permutations, claiming secu…

🅲 hạng C
26
Mitigating fix reversal: Counterfactual constraints for function-level vulnerability detection
📄 Paper arXiv cs.CR 11 giờ trước

arXiv:2611.24489v1 Announce Type: new Abstract: Function-level vulnerability detectors often exhibit fix reversal, assigning a higher vulnerability probability to a fixed version than to its vulnerable counterpart. Fixes usually lengthen functions, and larger length increases ar…

🅲 hạng C
25
JEV vs. LLMs: A Comparative Analysis for Phishing Email Detection
📄 Paper arXiv cs.CR 11 giờ trước

arXiv:2611.23683v1 Announce Type: new Abstract: Phishing remains a major source of credential theft and fraudulent payments, and email security systems must classify large message volumes reliably, quickly, and at manageable cost. Large Language Models (LLMs) offer flexible text…

🅲 hạng C
25
PGPO: Prototype-Guided Progressive Obfuscation for Privacy-Preserving LLM-Enhanced Recommendation
📄 Paper arXiv cs.CR 11 giờ trước cũng có trên: HF Daily Papers

arXiv:2611.23236v1 Announce Type: cross Abstract: LLM-enhanced recommender systems encode item side information into semantic embeddings, but these embeddings may leak sensitive textual attributes through inversion attacks. Existing input-side defenses rely on trusted collection…

🅲 hạng C
24
Human-AI Mutualism Is Unstable under Capability Asymmetry
📄 Paper arXiv cs.AI 11 giờ trước

arXiv:2611.23322v1 Announce Type: new Abstract: One hope for a good human future alongside advanced AI rests on enduring mutualism: humans and AI will need each other, so the relationship will stay good for both. We argue that this hope fails as AI capability grows. Bargaining g…

🅲 hạng C
24
Training Language Models for Introspective Oversight
📄 Paper arXiv cs.AI 11 giờ trước

arXiv:2611.23365v1 Announce Type: new Abstract: Language models increasingly exhibit behaviors that are difficult to detect in transcripts, such as reward hacking, deception, and sycophancy. Asking the assistant follow-up questions about its actions is unreliable, since models a…

🅲 hạng C
24
HardwareDx: A Foundational Graph Model System for Datacenter Machine Repairs
📄 Paper arXiv cs.AI 11 giờ trước

arXiv:2611.23398v1 Announce Type: new Abstract: The rapid scale-up of AI infrastructure has made datacenter reliability a cornerstone of the cloud business economy. Since hardware failures in hyper-scale AI clusters can stall multi-million dollar training workloads, the downtime…

🅲 hạng C
24
BOS Summary: The First Token Matters
📄 Paper arXiv cs.AI 11 giờ trước

arXiv:2611.23508v1 Announce Type: new Abstract: Large vision-language models (LVLMs) and language models (LLMs) often exhibit attention sinks, whereby particular positions, such as the beginning-of-sequence (BOS) token, receive a disproportionate share of attention. Under standa…

🅲 hạng C