Newsletter archive
Applied Signals Weekly: 2026-10-04
Sep 28, 2026 to Oct 04, 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.
- A model guide for the GPT-6 family — Learn how startups can choose GPT-6 models, tune reasoning effort, improve prompts and skills, coordinate tools, and prepare workflows for production.
- ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization — Automated harness optimization can substantially improve LLM agents by iteratively updating their prompts, tool interfaces, and control logic from execution feedback. However, existing methods primarily optimize how the…
- ROWBench: Do Video Models Render What the Program Specifies? — Programmable world models separate executable dynamics from visual generation, offering a promising foundation for next-generation game engines. However, their visual adherence to explicit rules and interactions remains…
- Claude’s hillclimb loop for AI agents: start with production traces — Anthropic's Claude hillclimb loop designs evals and improves agents one change at a time. Here's how to run that loop against production traces in Arize AX.
- Introducing Arize AX MCP: When to use MCP, CLI, or skills — MCP, CLI, and skills are three ways to extend an agent with the same platform. The question is no longer which one wins. It is where the agent runs, and who is asking.
- KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux… — LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existing evaluations focus on knowledge-based assessments or end-to-end…
- Prompt caching benchmark: high cache reuse doesn’t always mean lower cost — We benchmarked prompt caching across DeepSeek, GLM, GPT, and Claude using Harbor evals and Phoenix traces, so we could compare cache reuse, estimated cost, and latency on the same multi-turn shopping assistant…
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
- Agent Evaluation Loops Replace Static Harnesses (weekly trend)
- Oct 04, 2026 RPG, VISTA, Alyx memory files, and VectraYX tool-call diagnostics
- Oct 03, 2026 OmniSeek multimodal evidence acquisition and ActiveSaddler bandit curricula
- Oct 02, 2026 CTMC tail-aware memory, stale state delegation, and Qwen3 microtask gating
- Oct 01, 2026 AREX-2, Sage, TomasuLLM and PANDA agent coordination results
- Sep 30, 2026 IMPACT intent coordination and L*-DFA routing results
- Sep 29, 2026 MARCH ties, TokenCast token forecasts, and ScopeBench scope violations
- Sep 28, 2026 ADF-EA assurance, AgentWorld CCE, HiCoMER validity-aware memory
Subscribe
Get Applied Signals weekly newsletter in your inbox