Newsletter archive
Applied Signals Weekly: 2026-10-11
Oct 05, 2026 to Oct 11, 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.
- Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training… — Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it…
- Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration — While learning dexterous manipulation from a single human video offers a promising alternative to costly robot demonstrations, many recent methods predominantly imitate demonstrated motions. Such strict motion matching…
- ICYMI: What landed for AI builders in September 2026 — A monthly recap of the latest Amazon Bedrock, Amazon Bedrock AgentCore, and Strands updates from September 2026: broader model choice, faster serverless agents with built-in evaluation, and automated knowledge base…
- RoboRSI: Stable, efficient, and reusable robot self-evolution in complex… — A generalist robot should not only perform diverse tasks but also improve through experience, turning what it learns during execution into capabilities that later tasks can reuse. Robot agents that act through code can…
- How to build great out-of-the-box user experiences with Managed Deep Agents — Managed Deep Agents includes a new API for managing reactions for your distributed agents, and a system to dynamically assign emoji responses with your instrument of choice. Learn more.
- Asana cuts model costs 76x in browser tests with GPT-6.1 Sol — Using GPT-6 Astra in Codex, Asana made its browser agent 76x cheaper and 5x faster in tests to offer customers more capable models.
- Strands Box: The Big Picture — Strands Box, now in developer preview, is an open source local sandbox for AI agents that pairs operating-system isolation with Dogwood semantic policy. Here's why semantic policy matters, and how Box's design follows…
Worth watching
- frameworks + tool-use: hype or repeatable pattern?
- planning + tool-use: hype or repeatable pattern?
- frameworks + planning: hype or repeatable pattern?
Read the full analysis
- Agent frameworks converge on harnessed tool-use (weekly trend)
- Oct 11, 2026 Strands Evals, RoboRSI, and Managed Deep Agents 0.8 updates
- Oct 10, 2026 Agent Lightning v1.0 SWE-bench gains and OneSearch-VL evidence graphs
- Oct 09, 2026 Synthesis Through Simulation, BrickBench, SWE-Journey evaluation updates
- Oct 08, 2026 MAScope topology-conditioned diagnosis and Long-WAM long-history robot control
- Oct 07, 2026 AdvSim2Real robustness, SharedVisCache reuse, Trust-Gated control
- Oct 06, 2026 H-JEPA hierarchical planning, Harbor/Phoenix benchmarking, PrisMem memory gains
Subscribe
Get Applied Signals weekly newsletter in your inbox