Newsletter archive
Applied Signals Weekly: 2026-09-27
Sep 21, 2026 to Sep 27, 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.
- Coding Agents for Generalized Task and Motion Planning Problems — Task and motion planning (TAMP) problems remain difficult even with full observability and object-centric states because discrete decisions are tightly coupled to geometric, kinematic, and dynamic constraints.…
- Rolling-WAM: World Action Models with Rolling Imagination — World Action Models (WAMs) couple action generation with future visual prediction for robotic manipulation. However, completing the joint video-action denoising process at each replanning cycle incurs substantial…
- Advancing Private AI Compute with secure, server-side memory — Introducing private, server-side memory to Private AI Compute for personal AI.
- How to build a remote evaluator in Arize AX with Jev — Evaluate agent responses with Jev and Arize AX. Build a FastAPI remote evaluator, return labels and scores, and choose a threshold for your data.
- Real-time LLM guardrails with Jev: comparing latency and cost — Compare Jev and GPT-5.4 nano for real-time LLM guardrails, with demo results on latency, cost, and checks on agent inputs, replies, and tool calls.
- WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation — Video generation begins in text space by authoring a cinematic screenplay, then materializes into pixels. As contemporary video generators scale to 30 seconds and faithfully follow complex conditions, the textual prompt…
- What changes when AI agents use your software — Daytona cofounder Ivan Burazin wants agents that can finish the job within the authority they have been given. His interview offers a starting point for examining how agents use your software.
Worth watching
- evaluation + planning: hype or repeatable pattern?
- planning + tool-use: hype or repeatable pattern?
- evaluation + tool-use: hype or repeatable pattern?
Read the full analysis
- Trace Integrity Becomes the New Bottleneck (weekly trend)
- Sep 27, 2026 Trace integrity risks and Rolling-WAM replanning speedups
- Sep 26, 2026 HEXIS, IterSynth, and ExplorationBench agent control and evaluation
- Sep 25, 2026 terminus-2 reward hacking, Codetta steganography, Skilder access control
- Sep 24, 2026 CoMed selective escalation, SkillApt paired evidence, ToolUniverse silent tool failures
- Sep 23, 2026 AI Agent Populations indirect tipping attacks and Agensh scaling in agent societies
- Sep 22, 2026 GovSim-SelfGovern collusion study, Trace walkthroughs, DolphinBench memory evals
- Sep 21, 2026 Evolving Procedural Memory, Proxifield routing, APort Vault authorization
Subscribe
Get Applied Signals weekly newsletter in your inbox