Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The server exposes Langfuse's LLM observability data — traces, costs, and usage trends — through the MCP interface, making analytics accessible via natural language rather than direct API calls.
GameCraft-Bench exposes a concrete ceiling on current coding agents' ability to produce fully playable games, showing that even the best frontier models fall below 41.46% on a task requiring integrated scripts, scenes, assets, and runtime interaction — a gap that partial code-generation benchmarks do not capture.
ReproRepo replaces the manual curation bottleneck of prior reproducibility benchmarks with a scalable, naturally occurring signal from GitHub issues, enabling ongoing large-scale evaluation of LLM agents on real-world ML paper auditing.
Because any single harness component can move benchmark scores by margins comparable to those between adjacent model generations, end-to-end scores can misattribute performance gains and mislead practitioners trying to improve agentic systems.
The paper identifies task decomposition — not retrieval — as the binding constraint in multi-skill agent planning, and SAD's single-iteration fix raises decomposition accuracy by over 32 percentage points, directly improving how reliably agents can assemble executable plans from large real-world skill libraries.
Codify's stateless, config-as-code approach to dev machine setup — backed by an AI agent that avoids raw shell command generation — offers a reproducible alternative to ad-hoc environment provisioning scripts.
RAGSync removes the need to write any ingestion or indexing code to give an LLM semantic search over a custom knowledge base, replacing what would otherwise be a bespoke RAG pipeline with a single YAML config.
VulnFeed brings EPSS-prioritized, lockfile-aware CVE scanning directly into MCP-compatible coding agents, replacing broad CVE noise with targeted, fix-ready alerts for a project's actual dependencies.
ctx addresses the workflow fragmentation that arises when running multiple coding agents in parallel by consolidating supervision, review, and merge state into a single local surface rather than across scattered terminal tabs and browser windows.
Vercel Connect removes the standing risk of leaked long-lived provider tokens by ensuring no provider secret ever resides in the app, replacing broad standing grants with short-lived, task-scoped credentials that expire automatically and can be revoked without a full secret rotation.