cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5484, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

27
EvoDisco: Strategy Discovery for Evolving Agent Memory
📄 Paper arXiv cs.AI 18 giờ trước

arXiv:2611.22102v1 Announce Type: new Abstract: Large language model agents accumulate experience in memory, and how that memory evolves during interaction is as important as what it stores. Recent methods update memory online, yet both the operators that transform memory and th…

🅲 hạng C
26
EvoX: Rethinking the Agent Harness as a Runtime Policy
📄 Paper arXiv cs.AI 5 ngày trước

arXiv:2611.15006v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly interact with tools and environments, yet plausible model decisions do not always translate into successful execution due to tool-call mismatches, interrupted workflows, and unsupporte…

🅲 hạng C
26
PolicySniff: Inferring Agent Policy States through Shared-GPU Execution
📄 Paper arXiv cs.CR 5 ngày trước

arXiv:2611.16158v1 Announce Type: new Abstract: LLM agents apply approval settings, such as whether to ask before a consequential tool call, through instructions in their system prompt, and operators keep these settings confidential by restricting access to prompts and responses…

🅲 hạng C
26
Agentic On-Policy Distillation Implicitly Reshapes LLMs' ReAct Patterns
📄 Paper arXiv cs.AI 1 ngày trước cũng có trên: HF Daily Papers

arXiv:2611.19244v1 Announce Type: new Abstract: On-policy distillation (OPD) transfers specialized capabilities to language-model agents, but its cross-domain effects on interaction remain unclear. We investigate how OPD reshapes ReAct interaction patterns across mathematics, AL…

🅲 hạng C
26
From Token Changes to Task Failures: Bit Flips in a Shared KV-Cache Block
📄 Paper arXiv cs.CR 18 giờ trước

arXiv:2611.22243v1 Announce Type: new Abstract: In LLM serving systems with prefix caching, each KV block of a shared system prompt is held in GPU memory as a single physical copy, which every request with that prompt reads. Our earlier work measured change and showed that one b…

🅲 hạng C
26
SPLICE: Structured Prompt Local Iterative Combinatorial Evolution
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.18883v1 Announce Type: new Abstract: Natural language optimization (NLO) improves an agent by having a model critique and rewrite its natural language policy parameters: system prompts, tool instructions, reasoning directives, few-shot demonstrations. These artifacts …

🅲 hạng C
24
Attacker Diversity Reduction in Adaptive LLM Red Teaming
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.19680v1 Announce Type: new Abstract: Reinforcement learning can make automated red-teaming more successful while narrowing the attacks it produces. Co-training an attacker and a defender with group-relative policy optimization (GRPO) has been reported to reduce attack…

🅲 hạng C
24
Envisioning Agentic Robotics: A New Era of Robotic Systems
📄 Paper HF Daily Papers 6 ngày trước

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…

🅲 hạng C
24
LLMs are Vulnerable to Malicious Requests with Indistinguishable Intent
📄 Paper arXiv cs.CR 2 ngày trước

arXiv:2611.17818v1 Announce Type: new Abstract: Jailbreak attacks can circumvent the safety mechanisms of Large Language Models (LLMs) and lead to the generation of harmful or policy-violating content. We first examine eight jailbreak methods against an LLM-based filter and obse…

🅲 hạng C
23
Honest Brokers in AI Regulation: How Public Comments Introduce Evidence to Regulators
📄 Paper arXiv cs.AI 18 giờ trước

arXiv:2611.21948v1 Announce Type: new Abstract: The regulation of Artificial Intelligence is susceptible to various forms of capture by industry actors that hold undue influence over the policymaking process, due in part to their information advantage in developing these technol…

🅲 hạng C
23
Continuation-Guided LLM Evolution of Program Policies and Goal Compilers in Craftax
📄 Paper HF Daily Papers 5 ngày trước

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…

🅲 hạng C
23
A physics-constrained deep reinforcement learning method for autonomous mission planning of Titan deep space probes
📄 Paper arXiv cs.AI 5 ngày trước

arXiv:2611.15389v1 Announce Type: new Abstract: Titan is a compelling target for future deep space exploration, while its extreme Earth-Titan distance and complex environment make continuous ground-in-the-loop planning impractical. Existing planning methods, primarily developed …

🅲 hạng C
22
Policy Optimization With Multiple Verifiers via Pareto Rankings
📄 Paper arXiv cs.AI 1 ngày trước

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…

🅲 hạng C
21
Regularized Score Centering
📄 Paper HF Daily Papers 3 ngày trước

Asynchronous reinforcement learning increases training throughput, but data from stale policies and numerical mismatch between training and inference can destabilize learning. To stabilize off-policy learning, score centering (SC) removes the effect of reward baselines on the exp…

🅲 hạng C
21
JEPA4R: Embodied JEPA World Models with 4D Point Planning
📄 Paper HF Daily Papers 4 ngày trước

Joint-embedding predictive architecture (JEPA) world models predict future embeddings instead of pixels and plan in latent space. Two challenges remain: 2D images leave the metric geometry that manipulation acts on implicit and entangled with appearance, and what these models ima…

🅲 hạng C
20
Self-Improvement Memory Enables Continual Recursive Self-Improvement
📄 Paper HF Daily Papers 6 ngày trước

Harness optimization is often studied with a fixed policy model and benchmark. When either changes, the optimizer must decide which parts of an evolved harness to reuse or revise, but the harness alone may not explain why earlier edits were made or how they performed. In this wor…

🅲 hạng C