Search papers, labs, and topics across Lattice.
Affiliation:
3
0
8
6
LLM agents achieve dramatic efficiency gains in long-horizon research by offloading conversational history to a central harness, enabling focused, role-specific contexts for each task.
Reasoning in base LLMs can be unlocked by simply prepending specific tokens, matching RL-tuned performance on math and coding.
Even advanced LLMs struggle to replicate human researchers' ability to find inspiring prior work, highlighting a significant gap in AI's scientific intuition.
