AgenC now defaults to one agent after multi-agent systems fell 39%–70% behind
tetsuoai · x · 2026-07-23
AgenC defaults to one agent after multi-agent benchmarks fell 39%–70% behind
An X thread explains why AgenC 0.9.0 now defaults to one agent, isolates parallel writers, and treats integration as an evidence problem instead of a prompt instruction.
The cited evidence comes from two benchmark results:
- CAID’s PaperBench Code-Dev isolation ablation:
- shared-workspace multi-agent: 55.5
- single agent: 57.2
- worktree-isolated multi-agent: 63.3
- Scaling Agent Systems on sequential PlanCraft:
- every evaluated multi-agent architecture finished 39.1%–70.0% below the single-agent mean
The thread’s takeaway is that parallel agents sharing one checkout can interfere with each other even if prompts warn them not to. AgenC therefore gives every parallel writer a spawn-unique Git worktree and only returns an integration reference when the output is committed and clean.
Related event: AgenC Defaults to Single Agent After Multi-Agent Setbacks(4 posts)→
More from coding & agent
- Creator shares a Codex + ChatCut workflow for turning long videos into platform clips — yihui_indie · 2026-07-23
- Claude Code’s CLAUDE.md is only context; hard rules need PreToolUse hooks — thisdudelikesAI · 2026-07-23
- Claude Code’s /context and /memory commands reveal which memory files are actually loaded — thisdudelikesAI · 2026-07-23
- Add Claude Code rules only after the same mistake shows up twice — thisdudelikesAI · 2026-07-23
- Claude Code’s auto memory writes project notes to disk and loads only the first 200 lines — thisdudelikesAI · 2026-07-23
- Claude Code supports @path imports in CLAUDE.md to reuse shared rules across repos — thisdudelikesAI · 2026-07-23