2 papers
cs.LG2026
Input-Blind Controls Produce Substantial Oracle Headroom for Layer Programs in Multiple-Choice Evaluation
Yibei Guo, Rui Liu
Adaptive computation aims to improve language-model inference by tailoring execution to each input. For layer programs, oracle evaluations use known answers to estimate the potenti…
cs.AI2026
Evolving in the Agent Jungle via History-Informed Opponent Awareness
Zhaofeng Zhang, Linhan Xia, Rui Liu +3
Learning to adapt strategies through interaction is a key step toward more general and autonomous LLM agents. Existing approaches typically achieve behavioral adaptation by revisin…