GIANTS-4B, trained with RL on a new 17k-example benchmark of parent-to-child paper insights, achieves 34% relative improvement over gemini-3-pro in LM-judge similarity and is rated higher-impact by a citation predictor.
Synthesizing scientific literature with retrieval-augmented language models.Nature, pages 1–7
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
DeepWeb-Bench is a benchmark requiring massive cross-source evidence collection and long-horizon derivation, with evaluations on nine frontier models showing derivation and calibration as primary failure modes.
citing papers explorer
-
GIANTS: Generative Insight Anticipation from Scientific Literature
GIANTS-4B, trained with RL on a new 17k-example benchmark of parent-to-child paper insights, achieves 34% relative improvement over gemini-3-pro in LM-judge similarity and is rated higher-impact by a citation predictor.
-
DeepWeb-Bench: A Deep Research Benchmark Demanding Massive Cross-Source Evidence and Long-Horizon Derivation
DeepWeb-Bench is a benchmark requiring massive cross-source evidence collection and long-horizon derivation, with evaluations on nine frontier models showing derivation and calibration as primary failure modes.