Search papers, labs, and topics across Lattice.
4
0
7
7
TRAIL is presented, an adversarial agentic learning framework for robust C-to-Rust translation that transforms trace-specific experience into robust, reusable, and generalizable translation knowledge.
DeepRepoQA achieves substantial performance gains in code repository question answering by enabling LLM agents to perform multi-hop reasoning through systematic exploration.
Temporal confidence allows for adaptive computation in parallel reasoning, leading to a 32% reduction in latency without sacrificing accuracy.
ACQUIRE turns knowledge gaps into actionable insights, boosting software repair accuracy by over 4% while keeping costs low.
