Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
IAPO: Influence-Aware Policy Optimization for Credit Assignment in Multi-Turn Service Agents
Bo Ren, Yirong Mao, Yi Yang +1
Large Language Model (LLM) agents increasingly solve long-horizon tasks through multi-turn interactions with users and external tools. In these settings, relevant task information…
cs.LG2026
DUET: Dual-Teacher On-Policy Distillation via Same-Weight Disagreement for Prohibition Compliance
Zihan Li, Feifei Li, Wenhui Que
Real-world LLM deployments increasingly rely on runtime-injected prohibitions--enterprise policies, PII redlines, tool boundaries--that vary per request and per tenant. Conventiona…