Analytics Vidhya·
Most search agents try to handle too many jobs at once. They generate new queries, remember what they have already explored, collect evidence, and decide what is relevant as the search keeps expanding. That can make the whole process messy, expensive, and hard to control. Harness-1 takes a simpler approach. Built with researchers from UIUC, […] The post Harness-1: The 20B Retrieval Subagent That Beats GPT-5.4 at Search appeared first on Analytics Vidhya.
Read full articleA hands-on walkthrough of a hybrid local-cloud workflow using Gemma 4 and GPT-5.4, with reasoning and structured outputs The post Stop Choosing Between Local and Cloud LLMs: A Field Guide to Hybrid Patterns appeared first on Towards Data Science.
AI-driven optimization in drug synthesis accelerates R&D timelines, potentially reducing costs and expediting market entry for pharmaceuticals. The post GPT-5.4 improves Chan-Lam coupling yields in drug discovery appeared first on Crypto Briefing.
OpenAI and Molecule.one show how a near-autonomous AI chemist using GPT-5.4 improved a key drug-making reaction, advancing medicinal chemistry research.
UIUC and Chroma's Harness-1 is a 20B retrieval subagent trained with reinforcement learning inside a stateful search harness. The harness maintains the bookkeeping — candidate pool, importance-tagged curated set, evidence graph, verification records — while the policy decides what to search, curate, verify, and when to stop. It reaches 0.730 average curated recall across eight benchmarks, beating the next open subagent by 11.4 points and trailing only Opus-4.6. Weights and harness code are public. The post Meet Harness-1: A 20B Retrieval Subagent Trained With Reinforcement Learning Inside a Stateful Search Harness on gpt-oss-20b appeared first on MarkTechPost.
OpenAI frontier models GPT-5.5 and GPT-5.4, and Codex, the OpenAI coding agent, are now generally available on Amazon Bedrock. Deploy frontier models on Bedrock's high performance inference engine with built-in security, governance, and pay-per-token pricing.
Microsoft Research introduces Webwright, a terminal-native browser agent framework that replaces click-trace web automation with reusable Playwright scripts. Using a single agent loop across three modules and roughly 1,000 lines of code, Webwright powered by GPT-5.4 reaches 60.1% on the long-horizon Odysseys benchmark and 86.7% on Online-Mind2Web — the highest AutoEval score among open-sourced harness recipes. The post Microsoft Research Releases Webwright: A Terminal-Native Web Agent Framework That Scores 60.1% on Odysseys, Up from Base GPT-5.4’s 33.5% appeared first on MarkTechPost.
OpenAI just announced its new GPT-5.5 model, which the company calls its "smartest and most intuitive to use model yet, and the next step toward a new way of getting work done on a computer." OpenAI just released GPT-5.4 last month, but says that the new GPT-5.5 "excels" at tasks like writing and debugging code, doing research online, making spreadsheets and documents, and doing that work across different tools. "Instead of carefully managing every step, you can give GPT-5.5 a messy, multi-part task and trust it to plan, use tools, check its work, navigate through ambiguity, and keep going," according to OpenAI. The company also notes that … Read the full story at The Verge.
A new memory framework from Google Cloud AI Research and UIUC gives LLM agents the ability to distill generalizable reasoning strategies from both successful and failed experiences — and combines that with test-time scaling to create agents that genuinely improve over time. The post Google Cloud AI Research Introduces ReasoningBank: A Memory Framework that Distills Reasoning Strategies from Agent Successes and Failures appeared first on MarkTechPost.
