RAG

2026-10-26

RESEARCH · 1 SOURCE · arXiv cs.AI

arXiv paper shows 'warped' tool output formatters can mislead agents and verifiers

A new arXiv preprint (arXiv:2610.32110v1) demonstrates that tool output formatters which omit metadata (like search limits, result caps, or identifier namespaces) can cause agents and their automated verifiers to produce or accept incorrect answers; the authors reproduce failures in a production RAG system used at the Pilsudski Institute and find warped formatters in open-source agents OpenClaw and Hermes, opening PRs to fix them (OpenClaw's fix merged).

7.0

2026-10-16

CODING · 1 SOURCE · InfoQ AI, ML & Data Engineering

InfoQ webinar panel highlights silent failures and governance for AI agents

An InfoQ webinar titled “AI in Production: What Breaks, What Works, and Who Approves It?” gathered ThoughtWorks practitioners and security/privacy experts to discuss operational challenges of agentic systems, including semantic and embedding drift, RAG leakage, model memorization, and the scaling gap for human code review as coding agents produce more production code. Panelists recommended treating evals as persistent infrastructure, shifting checks left in the harness, using mutation testing and continuous tracing, enforcing agent identities and tiered access, red‑teaming, and isolating secrets to limit blast radius.

6.0

2026-10-07

COMPANIES · 1 SOURCE · AWS Machine Learning

Amazon adds real-time ACL verification to Quick and Bedrock Knowledge Bases for RAG

Amazon implemented a two-stage access-control approach for Amazon Quick and Amazon Bedrock Knowledge Bases: pre-retrieval ACL filtering against indexed attributes, followed by real-time verification with authoritative data sources (e.g., Google Drive APIs using service-account impersonation) to ensure RAG responses respect current permissions.

6.0

2026-10-05

CODING · 1 SOURCE · InfoQ AI, ML & Data Engineering

Elastic presents a reusable, production-grade evaluation framework for agentic AI

At QCon AI, Susan Chang (Principal Data Scientist at Elastic) described how Elastic moved from siloed, ad-hoc agent evaluations to a unified production-grade evaluation framework that combines LLM-as-judge and deterministic rules, connects Python data-science evals with TypeScript production code, and uses deep tracing to detect regressions across RAG and cybersecurity workloads while preserving domain context.

5.0

2026-09-25

RESEARCH · 1 SOURCE · arXiv cs.AI

META: Episodic-Memory Multi-Agent Trading Framework (arXiv:2609.28771v1)

A new arXiv preprint presents META, a RAG-like episodic-memory-augmented multi-agent framework for financial decision-making that combines specialized indicator agents (e.g., Trend, MACD, RSI, SMA, AVWAP, Heikin-Ashi) with a Decision Agent and a Memory module that stores and retrieves past trading episodes as market-state embeddings with outcomes and reflections. The authors report improved short-horizon directional accuracy and robustness by recalling similar past episodes and adaptively reweighting signals; the project code is released on GitHub.

6.0

2026-05-28

CODING · 1 SOURCE · Mistral AI

Search Toolkit enters public preview — open-source composable framework for AI search pipelines

Search Toolkit is being released in public preview as an open-source, composable framework to build production search pipelines for AI applications. It unifies ingestion, retrieval (BM25, dense embeddings, and hybrid), and built-in evaluation (recall, precision, MRR, NDCG), supports Connectors for live data, and is designed to run on cloud, on-premises, or edge infrastructure.

6.0