BELIEFWEAVER improves long-horizon agent recovery from earlier failures
A distilled 9B student gained 9.8 points over the native baseline and cut estimated teacher API cost by 54.8%.
40
Product
Terminus-2
- Mentions · 7d0
- Mentions · 30d2
- All mentions2
- First seenOct 7, 2026
- Last mentioned18d ago
Timeline
2 articles · newest firstOpera: A Verbal Critic Framework for Long-horizon Coding Agents
Opera, a persistent verbal critic, lifts coding-agent resolve rates by up to 15 points on SWE-Bench-style benchmarks.
52
Appears with
- Terminal-Bench 2.1product · 1
- BELIEFWEAVERproduct · 1
- Qwen3.5-9Bai model · 1
- OpenHandsproduct · 1
- DeepSWEproduct · 1
- SWE-Bench Proproduct · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.