Baitaphish
Security intelligence
SearchLatest briefing
Source

arXiv · Computer Science — Artificial Intelligence (cs.AI)

Published papers collected under the historical Computer Science — Artificial Intelligence (cs.AI) category URL.

Source ID: arxiv_cs_ai

14 item(s)
← Back to all sources
2026-08-21T08:52:06Z
Active Inference as Context Acquisition for AI Agents
1d53114a9274…
AI-governanceAI-safetyLLM-agents
Source →Open →
2026-08-16T13:04:32Z
BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environments
d1f38c860da5…
AI safetyCAD generationGUI agents
Source →Open →
2026-08-16T13:04:24Z
Interval Certifications for Multilayered Perceptrons via Lattice Traversal
9f1da410f1fe…
AI safetyLLM agentsLLM hallucination
Source →Open →
2026-08-16T13:04:17Z
Operating-Layer Controls for Onchain Language-Model Agents Under Real Capital
4336ce9971cd…
agentic-systemsartificial-intelligenceautonomous-agents
Source →Open →
2026-08-16T13:04:11Z
Math Takes Two: A test for emergent mathematical reasoning in communication
3057c4fa09e1…
agentic-systemsai-agentsai-safety
Source →Open →
2026-07-23T08:52:13Z
FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads
b34284d029b6…
LLM-securityadversarial-mlconfidential-computing
Source →Open →
2026-07-20T08:52:11Z
GraphDx: A Cost-Aware Knowledge-Enhanced Multi-Agent Framework for Sequential Diagnosis
eac4508ddfc6…
LLMsMIMIC-IVMedQA
Source →Open →
2026-07-16T08:52:18Z
OriginBlame: Record- and Token-Level Data Provenance for AI Training Datasets
cfd0b64daa81…
AI-insuranceAI-riskLLM-auditing
Source →Open →
2026-07-09T08:52:33Z
AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation
2d2564b3e241…
LLM-augmented-ABMPOMDPSageMath
Source →Open →
2026-06-29T08:52:12Z
AI-Model Network: Concept, Current State and Future
a177594bd125…
AI-ModelNetError-Aware GWM','DysLexLens','assistive AI','multimodal emotionFC-RL
Source →Open →
2026-05-05T08:52:10Z
TADI: Tool-Augmented Drilling Intelligence via Agentic LLM Orchestration over Heterogeneous Wellsite Data
276db49ff563…
LLM safetyRLHF/DPOagentic AI
Source →Open →
2026-04-06T08:52:17Z
Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic Web
17acd4987edc…
LLM agentsagent misalignmentagentic web
Source →Open →
2026-03-23T08:52:13Z
When both Grounding and not Grounding are Bad -- A Partially Grounded Encoding of Planning into SAT (Extended Version)
add3b5f465b9…
IsabelleItinBenchLean 4
Source →Open →
2026-03-16T08:52:17Z
Context-Enriched Natural Language Descriptions of Vessel Trajectories
de4d9f08628f…
AISAgentFuelLLM
Source →Open →