Ivo's contract agent hits 91% on Legal Agent Benchmark via River AI post-training
ibab · x · 2026-10-02
At its first user conference Inscribe, Ivo announced three developments: Ivo Collaborate (end-to-end contract workflow with AI reading, guardrails, and risk routing), the Ivo-Micro1 Contract Bench (a benchmark measuring whether AI edits to contracts are actually effective), and Ivo Sage, an open-source model post-trained with River AI that jumped from 70% to 91% on the Legal Agent Benchmark at lower cost than competitors.
River AI offers an RL and post-training stack via API, helping teams improve open-weight models' reasoning and tool use, with deployment on River Cloud or customer-owned GPUs.
More from coding & agent
- Cloudflare opens Artifacts beta: a Git-native filesystem for building the next GitHub for agents — neal_lathia · 2026-10-02
- Building a reliable risk agent without frontier models: $0.02 per sweep, 250x cheaper than an LLM judge — alexcovo_eth · 2026-10-02
- Dev builds Tyton, an MCP that lets AI agents set up Meta Pixel + CAPI for you — Foreign-Chipmunk-295 · 2026-10-02
- Grok launches Bot Marketplace letting users add specialized AI agents for engineering, sales and more — Polymarket · 2026-10-02
- One prompt builds an agent-agnostic TMDB MCP with generative UI via Grok — Baconbrix · 2026-10-02
- Arcmira MCP ships rapid backend updates for agentic video editing with Claude — zealcaiden · 2026-10-02