Modal Reproduces GRPO Training of a Search Agent on gpt-oss-20b
ivan_bezdomny · x · 2026-10-23
Modal demonstrated that its platform can now handle GRPO training end-to-end by reproducing @lujasper's "Training Search Agents with GRPO" work: training gpt-oss-20b to perform multi-turn agentic search over a corpus of SEC filings using keyword-matching, grep, and read tools.
The reproduction shows the training is stable and correct, giving developers a one-stop path to run RL training for multi-turn agents on Modal.
More from coding & agent
- Most new CVEs hit hand-written legacy code, dev pushes back on vibe coding security blame — HowDevelop · 2026-10-23
- Claude and Claude Code Merge: Anthropic Engineers Say Delete Your CLAUDE.md Every 6 Months — rubenhassid · 2026-10-23
- Engineers merging 4x more PRs at Imprint: Will Larson on speeding up code review — AxSaucedo · 2026-10-23
- 15 practical ways to hand off work to Grok Bot's cloud computer — even with laptop closed — XFreeze · 2026-10-23
- 3 Lessons from Rebuilding Compute for AI Agents: Safe Sandboxes, Near-Free Idle, Persistent Memory — Saboo_Shubham_ · 2026-10-23
- Local model agentic coding benchmark: 27B matches 125B, tool-calling is the lever — Joralk_ · 2026-10-23