10 selected stories for 2026-10-31, grouped by topic.
Edition details
Dates use UTC+8. The latest edition uses a day with at least 5 completed reports when available; until then an earlier edition may appear. There is no fixed delivery time.
The ChatGPT desktop app now supports Amazon Bedrock in AWS GovCloud (US), providing access to OpenAI frontier models while meeting data residency and stringent security requirements.
Configuration centers on API-mode sign-in, administrator-controlled requirements.toml policies, user config.toml settings, a named AWS profile, and network rules that allow only the Bedrock Mantle endpoint.
LibStructBench is a document-grounded benchmark for reconstructing sequencing-library structures and molecular workflows.
Frontier agents often produce approximately correct reconstructions but remain unreliable at exact reconstruction, particularly in molecular-state representation and workflow connectivity.
A new arXiv paper proposes a behavioral test called PoPLi to detect whether AI agents are colluding via secret encoded messages, even when the messages appear innocent. In a simulated market, PoPLi was significantly positive when a covert code was present and near zero otherwise, outperforming message-only monitors.
An arXiv paper evaluates AI-written smart contracts through execution rather than opinion, finding that AI judges and standard analysis tools miss obvious mistakes, and proposes an elicitation-first architecture that asks clients a short checklist of questions before generating code and verifies results against an independently written executable answer key.
WebAnything is a fully automated framework that reconstructs source-grounded, reusable web environments from real URLs without per-site engineering. It built 244 website artifacts across 14 domains and 53 categories, supporting 12,984 executed tasks, and outperformed human-assisted WebHarbor in a blind audit.
Amazon Bedrock AgentCore Session endpoints give each runtime session an authenticated URL that forwards any HTTP method, path, and WebSocket connection to the ports you allow. In this post, you deploy a coding agent that keeps a Vite website running in its session, then watch the live site update in your browser as the agent edits files.
A DataIQ and Databricks report, based on peer discussions at DataIQ Guild 2026, outlines five leadership disciplines and four foundations to help enterprises make grounded decisions and turn AI ambition into sustained value amid uneven readiness and expectations.
An arXiv study makes ontology checkers the object of study, comparing curated, LLM-generated, and data-derived ontologies as judges of LLM agent answers over knowledge graphs. It finds that on UniProt, a curated ontology flags more correct answers than alternatives, but on real agent answers its flags are only marginally more precise than random.
LRMoE is a memory-aware MoE training system that jointly recalibrates backward demand and balances retained workload, planning retention quotas and expert placement during forward execution, and selecting token-expert pairs based on contribution during backpropagation. Experiments on Qwen3-30B-A3B and GLM4.5-106B-A12B show 21.2-44.8% reduction in cumulative MoE-layer training time to fixed-loss targets relative to SYMI.
OpenFrontiers introduces a cross-disciplinary corpus of 12,151 open research problems and a retrospective math benchmark of 200 problems with Lean 4 formalization, evaluated under closed-book, frozen-retrieval, and live-web conditions. Testing seven LLM agents shows closed-book rediscovery is rare (at most 7 of 40 resolved problems), while live-web success largely reflects retrieval of published solutions.
ThinkJev introduces a training-free framework that builds fast and slow systems from a single hybrid-thinking model to calibrate typed decisions. A statistical test on labeled dev data ensures System 1 only answers alone when its accepted answers stay under a target error rate; remaining decisions escalate to thinking with early stopping, achieving near always-think accuracy at 72% of the thought tokens.
This paper introduces a localized posterior inference framework that weights observation likelihoods by proximity to a target context and uses a conditional normalizing flow for amortized variational inference. It addresses model discrepancy where a single calibration parameter fails across the context domain. Twin experiments with the Branin-Hoo model and a single-column ocean k-ε turbulence closure show reduced aggregate predictive errors compared to global posterior and deterministic calibration.