FORKSCAPE's design follows published research. Every card links to the paper.
Model quality drops 39% on average as a linear chat grows. The longer the thread, the worse every answer gets.
Microsoft Research · arxiv.org/abs/2505.06120 ↗ The fix — FORKSCAPE is this, productized. −58%Branching cuts context size 58.1% and improves response quality. Isolated branches beat one growing transcript.
arXiv · arxiv.org/abs/2512.13914 ↗Agents act by writing and running code instead of emitting brittle tool schemas. Shipped as our Code Agent mode.
arxiv.org/abs/2402.01030 ↗Cost-aware triage before any fan-out: wasteful multi-agent runs are refused up front, not billed and regretted.
arxiv.org/abs/2605.05007 ↗Unchanged re-runs replay from cache and cost 0 tokens. Only edited nodes — and what depends on them — run live.
arxiv.org/abs/2605.06365 ↗Build insights are distilled into durable project knowledge, so every canvas starts smarter than the last.
arxiv.org/abs/2510.04618 ↗Your corrections become enforced rules. Fix an agent once and the fix persists across future runs.
arxiv.org/abs/2606.13174 ↗A post-run judge scores deliverables against a rubric, with one bounded revision round — quality without infinite loops.
arxiv.org/abs/2501.19306 ↗