Search papers, labs, and topics across Lattice.
5
2
9
12
Sustained self-improvement in LLM agents is achievable through a novel adaptive framework that outperforms traditional methods in dynamic task environments.
Mid-tier LLMs outperform their stronger counterparts in harness self-evolution, challenging assumptions about model capability and adaptability.
Domain-specific scientific models, previously siloed from LLM agent systems, can now be orchestrated for complex reasoning tasks via the Eywa framework, unlocking performance gains on structured data.
Current multimodal LLMs still struggle to integrate information and reason critically when assessed on real scientific papers, despite progress on isolated tasks.
Forget imbalanced LoRA usage: ReMix leverages reinforcement learning to route effectively among LoRAs, boosting performance in parameter-efficient fine-tuning.
