Policy dependency / Stack layer
Agentic Workflows Reveal Their Dependency Graph Only at Runtime — ASGE-RR Reserves Capacity for Calls That Haven't Happened Yet
arXiv 2608.06033
Stack layer / Contrast
Generative Reward Models Underperform in RL Because They Rank, Not Score — RRC Fixes the Mismatch
arXiv 2608.06310
Stack layer / Contrast
PaDoc Decodes Document Layout and Content in Parallel Instead of Sequentially — 67-118% Higher Throughput, 39-55% Lower P95 Latency
arXiv / HuggingFace Daily Papers (14 upvotes)
Policy dependency / Stack layer
AgentOPSD: Critic-Free Turn-Level Credit Assignment via Bayesian Belief Updates Hits 89.1% on ALFWorld With a 7B Model
arXiv / HuggingFace Daily Papers (57 upvotes)
Stack layer / Threat pattern
"Agentic Posture Vulnerability": A Vulnerability-Management Record for Agent Exposures That Have No CVE
arXiv 2608.05884
Stack layer / Update thread
Reinforcement Learning Applied to Stochastic Dynamics on Persistence Diagram Space
arXiv 2608.06276
Stack layer / Contrast
Activity Frames: Compiling a Day of Screen Capture Into Agent Memory Deterministically — 86x Smaller in 68ms, 98.4% Answer Accuracy vs 66-80% for LLM Summaries
arXiv / HuggingFace Daily Papers (15 upvotes)
Stack layer / Update thread
AppDeltaWorld predicts the next mobile screen as an executable HTML diff rather than a generated image
arXiv