Fin-SD tests how much hint signal self-distillation needs
On GPT-OSS-20B, a generic hint matched the full 3.03-point gain and used 9.5% fewer tokens than full-solution distillation.
42
AI model
gpt-oss-120b
- Mentions · 7d0
- Mentions · 30d1
- All mentions4
- First seenSep 2, 2026
- Last mentioned17d ago
Timeline
4 articles · newest firstBELIEFRAG: Making Adaptive RAG State-Aware under Evolving Evidence
BELIEFRAG tracks evidence state for adaptive RAG, matching quality with 35-39% fewer tokens than iterative retrieval.
48
MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution
MILO co-evolves agent harnesses and search strategy, beating prior harnesses on Terminal-Bench, PaperBench, and DeepSWE.
62
What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation
A new benchmark shows LLMs reach 68.3-93% accuracy propagating local revisions across conversationally generated artifacts, with parallel-sample selection most cost-effective.
30
Appears with
- gpt-oss-20bai model · 2
- qwen3.5-122bai model · 1
- qwen3.5-27bai model · 1
- Qwen3-32Bai model · 1
- Opus 4.8ai model · 1
- qwen3.5-9bai model · 1
- qwen3.5product · 1
- gpt-5.4-miniproduct · 1
- gpt-ossproduct · 1
- NTTvendor · 1
- gpt-5.4-miniai model · 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.