← Back to all news
arXiv Computation and Language By Arkajyoti Chakraborty, Adam Zernik, Ishika Kulkarni, Mudit Arora, Hugo Lin, Justin Chiu, Alessandro Di Bari, Neha Gupta, Andreas Stolcke

MADS: Multi-Agent Dialog Simulation for Robust Conversational Agents

Read the original on arXiv Computation and Language →

MADS (Multi-Agent Dialog Simulation) is a synthetic data generation pipeline that creates structured, diverse dialogue trajectories, including adversarial conversations that reflect realistic failure scenarios. The resulting MADS-Bench benchmark covers six domains, 55 personas, and 1095 conversations, with about 66% featuring failure-prone situations. Models trained with MADS are evaluated using a two-stage approach combining supervised fine-tuning and reinforcement learning with verifiable rewards to assess robustness.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv Computation and Language
Oct 8

ToolRACER: A Robust Agentic Conversation Emulation Resource for Agent Training and Evaluation

arXiv:2610.09163v1 Announce Type: new Abstract: Task-oriented conversational agents remain fragile under real world conversation scenarios as they rarely follow a predictable script, especially when...

By Arkajyoti Chakraborty, Aryan Tayal, Ishika Agarwal, Tanner Sorensen, Justin Chiu, Alessandro Di Bari, Neha Gupta, Andreas Stolcke
llmsagentsbenchmarkssafety
More like this →
arXiv AI
Jul 10

SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection

arXiv:2601. 02871v3 Announce Type: replace Abstract: Task-oriented proactive dialogue agents play a pivotal role in recruitment, particularly for steering conversations towards specific business outcomes, such as acquiring social-media contacts for private-channel conversion.

By Zhiyong Cao, Dunqiang Liu, Qi Dai, Haojun Xu, Huai Yuen Khor, Hao Wang, Huan He, Yafei Liu, Ke Ma, Ruqian Shi, Sicheng Zhou, Sijia Yao
agentsreinforcement-learningfine-tuning
More like this →
arXiv Computation and Language
Sep 28

Learning Natural Conversational Behavior in Tandem Speech-to-Speech Models with Randomized Guidance

The paper introduces a method called randomized intermediate guidance for training tandem speech-to-speech models, where a large language model (LLM) acts as a backend providing candidate responses while the user is speaking. Instead of simulating the backend’s guidance, the approach derives guidance directly from the conversation corpus, using target responses for informative guidance and randomly sampled responses to simulate irrelevant updates. Experiments on synthetic dialogues and 3.8k hours of real conversations show that this technique yields response quality comparable to LLM-generated baselines while improving natural turn‑taking and audio‑judge naturalness.

By Manato Yaguchi, Yotaro Kubo, Hikaru Asano, So Kuroki
llms
More like this →
arXiv Computation and Language
Sep 1

SIC-Agents: Benchmarking and Building an Adaptive Simulator for Pediatric Serious Illness Communication Training

The paper introduces SIC-Agents, a self‑improving framework designed to enhance simulation for pediatric serious illness communication (SIC) training. It presents two new benchmark suites—PitfallBench and DialogueBench—that assess simulators at both turn‑level and full‑dialogue levels, specifically addressing the unique challenges of multi‑party interactions and parental distress. Experiments demonstrate that SIC‑Agents surpasses static expert prompting, and the authors release the benchmarks for broader research use.

By Zihan Wang, Anita Marie Slominska, Rennie Bimman, Elizabeth Di Flumeri, Amanda Mayappo-Neeposh, Conall Francoeur, Tamara Ellen Carver, Xiao-Wen Chang, Doina Precup, Esin Darici Haritaoglu, Ismail Haritaoglu, Akshatha Arodi, Naomi Goloff
llmsagentsbenchmarks
More like this →