Search papers, labs, and topics across Lattice.
5
0
8
2
TACO reduces token overhead by 10% while boosting terminal agent performance by up to 4%, revolutionizing how we approach long-horizon reasoning tasks.
Over 10% performance improvement in experiment reproduction reveals the power of hierarchical coordination in multi-agent systems for computational research.
Industrial code generation gets a reasoning boost: InCoder-32B-Thinking leverages error-driven feedback and a code world model to achieve top-tier performance on complex hardware-aware tasks.
Code LLMs can achieve SOTA performance in agentic tasks by explicitly modeling the dynamic evolution of software logic across different training stages.
A new 32B code LLM trained specifically for industrial tasks crushes existing models on specialized domains like chip design and GPU kernel optimization, while remaining competitive on general coding benchmarks.
