Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

MODEL · ENTITY #3990

GPT-4.1

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

EVENT TIMELINE

3

RESEARCH · 1 SOURCE · Hugging Face

ALTK-Evolve (GPT-4.1) uses learned guidelines to top τ²-bench retail leaderboard without weight updates

ALTK-Evolve extracts short behavioral guidelines from agent trajectories using GPT-4.1 and appends them to the agent's system prompt; with no model weight updates it achieves 67.5% Pass^4 on τ²-bench retail (outperforming every retail entry in the Oct 12, 2026 leaderboard snapshot) and improves mean accuracy and Pass^4 in both retail and airline domains. The method uses GPT-4.1 as both the guideline extractor and agent (with GPT-5.5 simulating customers), compares guideline-support thresholds (sup3 vs lossless), and reports up to +10 percentage-point gains in Pass^4 versus baseline.

7.0

COMPANIES · 1 SOURCE · OpenAI

Ringg uses OpenAI GPT-5.6 to resolve up to 65% of customer calls

Ringg says it is using OpenAI's GPT-5.6 to power multilingual agents across voice, chat, WhatsApp and web, and that these agents resolve up to 65% of customer calls. The company claims this setup costs about 90% less than running the same agents on GPT-4.1.

6.0

COMPANIES · 1 SOURCE · AWS Machine Learning

Wood Mackenzie builds shared APEX agent platform on Amazon Bedrock AgentCore (GA Oct 2025)

Wood Mackenzie describes APEX (Agentic Platform for Energy eXperience), a shared enterprise agent runtime built on Amazon Bedrock AgentCore to avoid duplicated infrastructure across teams. The post explains why the team chose AgentCore (managed platform, model-agnostic, supports multiple agent frameworks and protocols, and reached GA in October 2025 with VPC/PrivateLink/CloudFormation support), and how APEX Studio centralizes observability, identity, scaling, and governance for internal and external agent apps like Woody and Lens AI.

7.0