SourceJul 6, 20262026-07-063 minVerified
Routing Small Models With Internal Confidence Signals
Examines routing in small LLMs using internal confidence signals to choose answering, search, document retrieval, or refusal.
SourceJun 23, 20262026-06-233 minVerified
Fara-1.5 Shows Data Bottlenecks in Computer-Use Agents
Fara-1.5 highlights why scalable data pipelines and verifiers, not just models, matter for computer-use agent training.
SourceMar 26, 20262026-03-263 minVerified
Rethinking LLM Agents as Adaptive Computation Graphs
View LLM agents as runtime-adaptive computation graphs to optimize accuracy, cost, latency, debugging, and control.
SourceMar 11, 20262026-03-114 minVerified
Executable Skills Library for Self-Improving RL Agents
Defines skills as executable function code and manages them online via create-run-update-on-fail-save-on-success loops.
SourceMar 7, 20262026-03-074 minVerified
Memory Admission Control for Reliable LLM Agents
A practical look at memory admission control for LLM agents, reducing long-term memory pollution while improving auditability and metrics.
SourceFeb 2, 20262026-02-023 min
My Bot Made the News, But It Can't Run Itself
A field report from running a community bot: what automation can do, and what still requires human operational control.
TrustedJan 23, 20262026-01-233 minVerified
Optimizing AI Agent Loops via OpenAI Responses API Architecture
Analyze how OpenAI's Responses API and MCP reduce AI agent latency and improve cache efficiency through server-side state management.