AgSpec Speeds Up Coding Agents Up to 4.76x with Retrieval-Based Speculative Decoding
Sumin Lee · hf · 2026-10-02
AgSpec brings retrieval-based speculative decoding into coding-agent pipelines, addressing two gaps in existing methods:
- Corpus design: retrieves from session, workspace, and global corpora, retains the ongoing session trajectory, and indexes opened files in the agent's emission format.
- Draft-length policy: bounds each agent's draft length via offline profiling and adapts it online from verification feedback.
On two repository-level multi-agent coding benchmarks, AgSpec beats five retrieval-based drafters and EAGLE-3 in most settings, raising throughput up to 4.37x at batch size 1 and 4.76x at batch size 16, with gains generalizing beyond repository settings.
More from coding & agent
- Handy Claude Code mod renders Mermaid diagrams right in the terminal — teropa · 2026-10-02
- Waysway Launches Travel MCP Connector for Hotels, Flights and Restaurants — modelcontextprotocol · 2026-10-02
- Desearch MCP Server Brings Real-Time AI Search on X and the Web to Agents — modelcontextprotocol · 2026-10-02
- Dev lets Sol Ultra improve his engine for 2 hours — usage barely moved 2% — Dimillian · 2026-10-02
- Meme: Developers hitting 'Allow' in Claude Code over and over — aishashok14 · 2026-10-02
- Microsoft's Autopilot isn't Scout 2.0: a private-preview shift to a Foundry-hosted cloud agent platform — pswider · 2026-10-02