ResearchReasoning Theater CoT Performative 80 Percent Token SavingsarXiv·high signalReasoning models form beliefs earlier than CoT suggests. Performative CoT dominates easy tasks. Probe-guided early stopping saves 80% tokens.SourceSource pagearXiv↳ Follow the threadPolicy dependency / Stack layerReason Less, Verify More: Deterministic Gates Catch a Silent Policy-Violation Failure in Tool-Using AgentsarXivStack layer / ContrastLong-Horizon-Terminal-Bench: Best Frontier Agent Clears Just 15% of Real Terminal Tasks, Mean 4.3%arXiv (Tencent Hunyuan) / HuggingFace Daily PapersStack layer / Update threadDominoTree Improves Speculative Decoding With Path-Dependent Tree DraftingarXivStack layer / Follow-up thread'When Is Routing Meaningful?' Fewer Than 10 Agents Recover Most Diversity in Model SocietiesarXivThreat pattern / Follow-up threadMalaika Grounds Agentic Malware Analysis in Domain, Program Semantics, and Threat IntelarXivContrast / Follow-up threadShared Selective Persistent Memory Lifts Agentic Task Completion to 96% and Cuts Per-Call Token Cost 97xarXivThreat pattern / Follow-up threadVEXAIoT: arXiv paper demonstrates autonomous IoT vulnerability exploitation using AI agentsarXivUpdate thread / Follow-up threadEvoAgentBench: A Benchmark That Isolates Whether Agents Can Turn Past Sessions Into Reusable ProceduresarXiv