Papers with multi-turn settings
Full-Duplex-Bench-v2: A Multi-Turn Evaluation Framework for Duplex Dialogue Systems with an Automated Examiner (2026.acl-short)
Copied to clipboard
Guan-Ting Lin, Shih-Yun Shan Kuan, Jiatong Shi, Kai-Wei Chang, Siddhant Arora, Shinji Watanabe, Hung-yi Lee
| Challenge: | Full-duplex speech agents are often half-duplice, alternating turns between user and system. |
| Approach: | They propose a streaming framework that integrates with an examiner that enforces staged goals under two pacing setups. |
| Outcome: | The framework reports fluency, multi-turn instruction following, and task-specific competence. |
DialoGPS: Dialogue Path Sampling in Continuous Semantic Space for Data Augmentation in Multi-Turn Conversations (2023.acl-long)
Copied to clipboard
| Challenge: | a context leads to various responses, and a response answers multiple contexts. |
| Approach: | They propose a method that augments open-domain dialogue generation from a many-to-many perspective. |
| Outcome: | The proposed method can augment open-domain dialogue generation tasks with automatic and human evaluation. |
Persona Jailbreaking in Large Language Models (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies focus on narrative or role-playing tasks and overlook how adversarial conversational history alone can reshape induced personas. |
| Approach: | They propose a framework that embeds semantically loaded cues into user queries to gradually induce reverse personas. |
| Outcome: | The proposed framework predictably shifts personas, triggers collateral changes in correlated traits, and exhibits stronger effects in multi-turn settings. |
Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs (2026.findings-eacl)
Copied to clipboard
| Challenge: | Reinforcement learning (RL) has re-emerged as a natural approach for training interactive LLM agents in real-world environments. |
| Approach: | They propose a variant that operates on a turn-level MDP formulation, instead of the commonly used token-level one. |
| Outcome: | The proposed method is more robust than the widely used GRPO algorithm and more efficient than token-level MDPs. |
STEP: Success-Rate-Aware Trajectory-Efficient Policy Optimization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing GRPO-based methods allocate sampling uniformly across tasks regardless of difficulty, propagate misleading learning signals and incur high sample-collection costs. |
| Approach: | They propose a framework that allocates sampling based on per-task success rates and performs fine-grained step-level optimization. |
| Outcome: | The proposed method improves sample efficiency and training stability over existing GRPO variants and three ablation variants on OSWorld and AndroidWorld. |