Guidance-TTT separates the generator into two roles.
Small test-time-trained guidance model beats adapting large LLM generators for discovery
Guidance-TTT separates strategic decision-making from solution implementation, outperforming prior methods across four scientific discovery benchmarks.
Chinese Tech
Chonghe Jiang · Ao Qu · Siyuan Liu · Ruoyun Ma · Zijian Zhou · Dingyi Zhuang · +6 more
Massachusetts Institute of Technology · Hong Kong Polytechnic University · ByteDance Inc. · National University of Singapore · Stanford University
Research Digest··2 min read
Jiang et al.
Why this paper
From ByteDance Inc. and 8 others
In one line
Guidance-TTT separates strategic guidance from solution execution, using a small test-time trained model to outperform prior methods.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks (4 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§