Search papers, labs, and topics across Lattice.
UC San Diego
3
0
4
Coding agents can now access repository context 8.7x faster, dramatically improving efficiency in navigating evolving codebases.
AI agents that ace isolated coding tasks fall apart when faced with the messy reality of continuous software evolution, dropping from 80% to 38% success rates in a new benchmark.
Current LLM memory systems falter when faced with the continuous, machine-generated interaction streams typical of real-world agentic applications, highlighting a critical need for causality-aware and tool-augmented memory architectures.
