Newsletter archive
Applied Signals Weekly: 2026-05-10
May 04, 2026 to May 10, 2026
In this week’s edition
This week’s edition surfaces where agentic systems face the sharpest pressure points: reliability under coordination, evaluation discipline, and the practical mechanics that keep multi-agent behavior stable over time.
- "OncoAgent: A Dual-Tier Multi-Agent Framework for Privacy-Preserving Oncology…
- AI agent evaluation: How to test, debug, and improve agents in production — Lessons from building and shipping Alyx, our AI agent
- Agent harnesses have an expiration date — A benchmark-driven look at why agent harnesses need adaptive finish logic as model behavior changes across Claude, GPT-4o, and Gemma.
- Parloa builds service agents customers want to talk to — Parloa leverages OpenAI models to power scalable, voice-driven AI customer service agents, enabling enterprises to design, simulate, and deploy reliable, real-time interactions.
- Running Codex safely at OpenAI — How OpenAI runs Codex securely with sandboxing, approvals, network policies, and agent-native telemetry to support safe and compliant coding agent adoption.
- Adaptive Parallel Reasoning: The Next Paradigm in Efficient Inference Scaling
- EMO: Pretraining Mixture of Experts for Emergent Modularity — Large language models are typically deployed as monolithic systems, requiring the full model even when applications need only a narrow subset of capabilities, e.g., code, math, or domain-specific knowledge.…
Deep dive
In the real world, the hardest part of scaling isn’t raw capability—it’s keeping failure modes observable and fixable as systems become more decentralized. When evaluation loops, instrumentation, and state-management drift faster than fixes, teams accumulate “invisible” debt that shows up only during deployment.
Worth watching
- evaluation and frameworks often showed up together—watch whether that pairing moves from discussion into repeatable engineering patterns.
- evaluation and planning often showed up together—watch whether that pairing moves from discussion into repeatable engineering patterns.
- frameworks and planning often showed up together—watch whether that pairing moves from discussion into repeatable engineering patterns.
Read the full analysis
- Control-flow-aware agents become the new bottleneck (weekly trend)
- May 09, 2026 StraTA, SkillOS, ScaleLogic, and Instrumental Choices results
- May 08, 2026 Partial Evidence Bench, SAT, and LATTE coordination evaluations
- May 07, 2026 Governed Memory, Stable Agentic Control, and Terminus-4B Token Savings
- May 06, 2026 Coordination as a Layer, MemFlow routing, QKVShare KV handoff
- May 05, 2026 Workspace-Bench, OpenSeeker-v2 and iWorld-Bench evaluation results
- May 04, 2026 Unauthorized installs in deployed multi-agent system; Foresight Arena α detection
Subscribe
Get Applied Signals weekly newsletter in your inbox