2 papers
cs.LG2026
EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents
Xuying Ning, Dongqi Fu, Tianxin Wei +13
Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, invoke tools, verify outcomes, and reuse experience across interactions.…
cs.LG2026
ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
Ruizhong Qiu, Hanqing Zeng, Yinglong Xia +15
Low-rank adapters (LoRAs) are a parameter-efficient finetuning technique that injects trainable low-rank matrices into pretrained models to adapt them to new tasks. Mixture-of-LoRA…