Live feed

huggingface.co · 2026-10-28 · Ranked: research watch · fresh 1.00 · score 2.82 · Context

NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt

arxiv.org · 2026-10-27 · Ranked: agentic + eval match · research watch · fresh 0.87 · score 2.74

PerceptRL: Making Visual Perception Rewardable in MLLMs from Answers to Interactions

Fine-grained visual perception remains a bottleneck during post-training of multimodal large language models (MLLMs), as perceptual errors can constrain gains from reasoning-focused optimization. Although image-captio... Context & related coverage →

arxiv.org · 2026-10-27 · Ranked: agent match · research watch · fresh 0.82 · score 2.63

Remembering Is Not Enough: Refining Memories and Learning When to Use Them in Multi-Agent Systems

Memory helps LLM-based multi-agent systems reuse experience, but stored advice can be flawed or applied in the wrong situation. Team-level success or failure alone cannot reliably show whether a memory needs correctio... Context & related coverage →

infoq.com · 2026-10-28 · Ranked: practitioner analysis · fresh 0.99 · score 2.59

Airbnb Cuts Recommendation Staleness from 2 Days to Seconds with Chronon

Airbnb extended its Chronon feature platform with Push Mode and Near Real-Time Model Transform to update sequence-based recommendation embeddings within seconds. The architecture reduced embedding staleness from nearl... Context & related coverage →

arxiv.org · 2026-10-27 · Ranked: agent + harness match · research watch · fresh 0.83 · score 2.51

A Harness Reducing over-Defensive Writing in Agents by Isolating Objections

When expanding a report, writing with agents may introduce a stronger claim than the article makes and then disclaim it. This is called over-defensive writing. We assume that this is because the agent is writing for r... Context & related coverage →

infoq.com · 2026-10-27 · Ranked: practitioner analysis · fresh 0.77 · score 2.29

Presentation: Serving LLMs at Scale: The Hidden KV Cache Advantage

Khawaja Shams shares a distributed systems perspective on scaling LLM inference stacks efficiently. He discusses practical strategies for optimizing GPU utilization, managing KV cache memory cliffs, leveraging tiered... Context & related coverage →

openai.com · 2026-10-28 · Ranked: agentic + codex match · frontier engineering · fresh 0.97 · score 1.59

Legora is building the agentic operating system for legal work

See how Legora uses OpenAI models, ChatGPT, and Codex to accelerate legal workflows, expand contract analysis, and free lawyers to focus on higher-value work. Context & related coverage →