Search papers, labs, and topics across Lattice.
Affiliation:
8
0
9
5
Current autonomous agents excel at practical problem-solving but often lack true methodological innovation, revealing critical gaps in their development as independent researchers.
HarnessCompass boosts agent performance by 22% in just five iterations, setting a new standard for generalization in automatic harness evolution.
Harness-assisted data synthesis boosts LLM forecasting performance by reducing temporal leakage and increasing sampling efficiency, leading to superior predictive capabilities.
Automatic harness evolution may not be the silver bullet for LLM performance it was thought to be, often lagging behind simpler scaling methods.
NaviCache redefines how we approach computational efficiency in video generation, achieving superior error judgment and performance without the burdens of traditional calibration methods.
The best LLM to answer a question isn't always the best LLM to *teach* the answer, and matching the "difficulty" of the explanation to the student's current abilities yields better learning.
Forget brittle orchestration layers – LLMs can internalize complex reasoning as a learnable "HeavySkill" that rivals external agentic frameworks.
LLMs can learn to reason *worse* from seemingly better training data: models trained on CoT data with lower loss can generalize poorly due to inheriting inefficient, divergent reasoning patterns.
