Search papers, labs, and topics across Lattice.
4
1
7
14
Open-source LLM agents can get a 27% performance boost in tool use by strategically injecting context tailored to address common failure modes.
Injecting demonstrations with a carefully annealed probability can drastically improve exploration in RLVR, even for tasks requiring novel reasoning or domain-specific knowledge.
Despite advances in LLMs, human-AI collaboration still significantly outperforms AI-only agents in domain-specific data science tasks, proving that human expertise remains crucial.
LLMs struggle to consistently use tools in dynamic environments, but a simple input reformulation strategy can boost performance by over 16% compared to standard methods like ReAct.
