Newsletter archive
Applied Signals Weekly: 2026-09-13
Sep 07, 2026 to Sep 13, 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.
- Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens — Many biological discovery problems require experiments to be selected sequentially under constrained budgets. CRISPR screening is a prominent example, as exhaustive perturbation testing is often infeasible and candidate…
- Code mode: Why your agent should code — Code mode gives an agent a sandbox instead of a longer tool list. Here is why it fixes the too-many-tools problem, what it costs you in sandboxing and debuggability, and when plain tool calling is still the right…
- Cognition helps Devin test its own work with GPT‑6 Astra — GPT‑6 Astra improves Devin’s ability to test software and show that it works, with the goal of helping engineers review less code and ship more.
- How I cut coding agent costs with model and harness routing — By routing planning, exploration, implementation, and review to different models, I reduced one recurring coding-agent workflow from roughly $100 to $15-$20 per run.
- MindTopo: Can Foundation Models Reason in Topological Space? — Spatial reasoning depends not only on metric properties such as distance, angle, and shape, but also on topological relations that remain invariant under continuous deformation. Cognitive science identifies these…
- The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement — Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement. We first use the Headroom-Closed…
- UniMPA: A Unified Memory-Prediction-Action Model via Action-Grounded Transition… — Recent advances in Vision-Language-Action (VLA) models have improved robotic manipulation, yet observation-to-action learning remains limited by a fundamental transition realizability gap, manifested in three tightly…
Worth watching
- evaluation + planning: hype or repeatable pattern?
- planning + tool-use: hype or repeatable pattern?
- frameworks + planning: hype or repeatable pattern?
Read the full analysis
- Harbor-Index and ARC-Bench show agent scores hide failure modes (weekly trend)
- Sep 13, 2026 MindTopo, COBRA-Skills, and UniMPA probe planning, cost, and memory
- Sep 12, 2026 QuantumQUBO, MaP-WAM and CLBench
- Sep 11, 2026 OpenDiscoveryTrace process-trace errors, ORCH hierarchies, backward-reasoning aggregation
- Sep 10, 2026 AhaBench, MERIT, ARC-Bench and Show-Harness evaluation results
- Sep 09, 2026 Procedural Graphs, AgentGrad, and SAEScientist-Bench agent evaluation
- Sep 08, 2026 RoboSPA benchmark, coding-agent routing costs, and APT-RAG reasoning trees
- Sep 07, 2026 MA-Evolve, Harbor Adapters, HarvestBench and VERGE evaluation signals
Subscribe
Get Applied Signals weekly newsletter in your inbox