Search papers, labs, and topics across Lattice.
Jilin University
2
0
5
Jointly optimizing high-level and low-level policies can dramatically enhance LLM performance in tool-use tasks, overcoming planner-executor misalignment.
Stop relying on LLMs to "hallucinate" reasoning paths – SEARCH-R uses a fine-tuned Llama3.1-8B model and dependency tree-based retrieval to navigate multi-hop question answering more reliably.
