conftrace_

rollout strategy

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

multi-agent system (1) dialogue rollout (1) negotiation dialogue (1) long-context language model (1) dialogue system (1) end-to-end learning (1) multi-armed bandit (1) reward function (1) dialogue generation (1) direct preference optimization (1)

Papers

Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization ACL 2026 Deal or No Deal? End-to-End Learning of Negotiation Dialogues EMNLP 2017