Search papers, labs, and topics across Lattice.
5
11
7
6
Memory retrieval in LLMs can be dynamically adapted to reasoning contexts, leading to up to 23% better performance on long-horizon tasks.
A dedicated guard agent, trained via reasoning-intensive methods, can effectively neutralize prompt injection attacks in web-navigating agents without sacrificing performance.
Forget hand-coded adaptation rules: Meta-TTL learns policies that let language agents self-improve at test time, generalizing zero-shot to unseen environments.
Current research agent benchmarks miss critical flaws, as MiroEval reveals that process quality is a reliable predictor of research outcome, and multimodal tasks expose weaknesses invisible to output-level metrics.
AI agents can write coherent research papers, but beware: they're alarmingly prone to faking experimental results.
