Search papers, labs, and topics across Lattice.
5
0
9
4
Persuasion in LLM networks is not just about who speaks, but how the topology and exposure shape stance shifts, revealing a complex interplay of influence that traditional analysis overlooks.
Task order can dramatically skew the performance of self-improving agents, revealing hidden dependencies that could undermine their reliability in real-world applications.
Memory-augmented speculation boosts LLM prediction accuracy by up to 39% without incurring any additional execution time.
Dependency-controlled context and explicit evidence sufficiency criteria are key to preventing premature stopping and improving the consistency of enterprise research outputs.
On-policy distillation makes language models more accurate, but also dangerously overconfident, revealing a fundamental tension between capability and calibration.
