Search papers, labs, and topics across Lattice.
Affiliation:
7
0
11
4
Wrapping standard CLI coding agents in a state-persisting orchestration layer beats unconstrained autonomous agents at research completeness without altering the underlying model.
No memory substrate is a one-size-fits-all solution; the right choice depends on the task, with broad retrieval boosting QA but hindering decision-making.
Decoupling perception from reasoning in visual tasks leads to a remarkable 93.2% accuracy on V-Star, showcasing a new paradigm for fine-grained visual reasoning.
OpenSkill enables LLM agents to autonomously evolve their skills and verification mechanisms in open-world settings, achieving superior performance without any target-task supervision.
Set representation models can be made robust to inference-time corruptions like outliers and missing data by training against a learned barycentric adversary.
LLM agents can now autonomously generate complex skills with multi-file dependencies, rivaling human-authored skills, thanks to a co-evolutionary verification process that doesn't need ground truth labels.
Even state-of-the-art LLMs struggle to adapt to mid-task changes in long-horizon web navigation, highlighting a critical gap in their ability to handle realistic user interactions.
