Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

MODEL · ENTITY #8428

GPT

Related event timeline, sources and context from the news index.

EVENT TIMELINE

3

RESEARCH · 1 SOURCE · arXiv cs.AI

Study (arXiv:2611.17639v1) examines what LLM agents act on vs. what users say

The paper uses presupposition theory to analyze when LLM agents proceed with actions (e.g., cancel reservations, delete folders) based on tool outputs versus user statements. It shows that agents frequently act without asking when lookups cannot distinguish one vs. multiple records, that listings stop most agents whereas simple counts do not, that user claims (e.g., “it is empty”) can reduce acting, and that latest Claude and GPT models tested opened a counted second record then never acted; a retail benchmark with same-name same-zip customers produced wrong-account writes in about a quarter of conversations unless lookups checked competing records or street data.

7.0

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

InfoQ: Platform engineering playbook for production LLMs

InfoQ publishes a platform-engineering playbook based on a retail inventory recommendation system that reduced hallucination rate from ~15% to ~1.5% without changing the foundation model by applying platform-level controls (automated retry loops, intent-validation gates, prompt registries, tool authorization, and custom instrumentation). The article links a companion GitHub repo with runnable examples that use a local llama3.1 via Ollama connected through LiteLLM and describes routing through foundation models such as Gemini and GPT under enterprise traffic.

7.0

RESEARCH · 1 SOURCE · arXiv cs.AI

CRISS: Retrieval-augmented chatbot to support cancer registrars (arXiv:2609.29075v1)

Researchers introduce CRISS (Cancer Registry Intelligent Support System), a retrieval-augmented generation (RAG) conversational assistant built on a domain-specific knowledge base of national cancer registry standards to provide citation-supported guidance to cancer registrars. In evaluations using an LLM-as-a-Judge protocol across easy/medium/hard question tiers, RAG configurations outperformed non-RAG baselines (mean grounding scores 0.62/0.56/0.59 vs 0.29/0.26/0.29); proprietary RAGs led on easy/medium items while local RAGs ranked highest on hard items, and RAGs achieved higher semantic-similarity scores overall.

6.0