Topic: agent

Latest on “agent”

The AI news that matters for people who make things — what happened, and how to put it to work in Grafy.

Verify by Doing lets AI agents self‑improve without external feedback

Researchers unveil Verify by Doing, a method that co‑evolves an agent’s execution and its own verification to learn from internal signals.

Try in Readeragentself-improvementverificationai

Grafy Research Lab22 h ago5 min read

EvoX Introduces a Runtime Policy to Boost LLM Agent Reliability

The new Rust‑based EvoX runtime applies a second, operational policy to LLM agents.

Try in Readerllmagent

Hacker News — front page5 days ago5 min read

ChatGPT Desktop now auto‑forwards SSH agents to remote machines

ChatGPT Desktop automatically forwards your local SSH agent to any remote host you connect to.

Try in Grafy Codesshsecurity

arXiv AIOct 31, 20265 min read

FilingLoop Benchmark Shows Self‑Evolving LLM Agents Improve SEC Filing Review

Researchers unveil FilingLoop, an interactive benchmark for LLM agents that review SEC filings.

Try in Readerllmbenchmark

MarkTechPostOct 26, 20265 min read

Tsinghua Open-Sources AKV, an SGLang Cache Server for LLM Agents

Tsinghua open-sourced AKV, an SGLang-based cache server for LLM agents, cutting costs by 27.7% in benchmarks. Learn how cache engineering reshapes context.

Try in Grafy Chattsinghuaakv