Challenge: Existing evaluation methods rely on static benchmarks or narrow task-specific datasets that fail to capture the open-ended nature of real-world interactions.
Approach: They propose a user Simulation framework for multi-turn AGent Evaluation that integrates top-down knowledge from business contexts and bottom-up knowledge from agent infrastructure.
Outcome: The proposed framework produces interactions that are more realistic and diverse while identifying up to 33% more agent errors.

Similar Papers

Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have evolved from statistical sequence predictors to sophisticated autonomous agents capable of reasoning, planning, and sustaining multi-turn conversa-tions.
Approach: They propose a system that instantiates a "Sentient Agent" that simulates human-like emotional changes and inner thoughts to provide a more realistic evaluation of the model in multi-turn conversations.
Outcome: The proposed framework measures the agent's higher-order social cognition in multi-turn conversations.
SAGE: A Generic Framework for LLM Safety Evaluation (2025.emnlp-industry)

Copied to clipboard

Challenge: Current safety evaluation methodologies focus on single-turn interactions with generic policies, failing to capture conversational dynamics of real-world usage and application-specific harms.
Approach: They propose a framework for customized and dynamic harm evaluations that employs prompted adversarial agents with diverse personalities based on the Big Five model.
Outcome: The proposed framework enables system-aware multi-turn conversations that adapt to target applications and harm policies.
Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data (2026.acl-long)

Copied to clipboard

Challenge: Recent research shows that LLM Agents can generate “believable” human behaviors via prompt-only methods, leaving open questions of whether they can accurately generate step-by-step actions in multi-turn interaction tasks.
Approach: They propose to use shopping data to evaluate LLMs' ability to accurately generate step-by-step actions in a multi-turn interaction task.
Outcome: The proposed model achieves 17.26% action generation accuracy and 33.86% F1 score on final purchase prediction, representing improvements of 5.4% and 13.85% over baselines.
SimUSER: Simulating User Behavior with Large Language Models for Recommender System Evaluation (2025.acl-industry)

Copied to clipboard

Challenge: Recommender systems are a key component of our day-to-day lives, but evaluation remains a challenge due to the gap between offline metrics and online behaviors.
Approach: They propose a framework that enables users to build believable human proxies from historical data.
Outcome: The proposed framework exhibits closer alignment with real humans than previous work, both at micro and macro levels.
Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems (2025.emnlp-main)

Copied to clipboard

Challenge: Existing platforms lack a mechanism for user actions to dynamically reshape the environment.
Approach: They propose a novel agent-based simulation platform for recommender systems with a robust interaction mechanism.
Outcome: The proposed platform improves the credibility of the simulation and replicates the Matthew Effect and Brand Loyalty.
LUMINA: Long-horizon Understanding for Multi-turn Interactive Agents (2026.findings-acl)

Copied to clipboard

Challenge: Large language models struggle on multi-turn, long-horizon agentic problems that require skills such as planning, state tracking, and long context processing.
Approach: They propose an oracle counterfactual framework for multi-turn problems that asks: how would an agent perform if it could leverage an or acle to execute a specific skill?
Outcome: The proposed framework allows for precise oracle interventions without confounding effects present in real-world benchmarks.
Efficient Agent Evaluation via Diversity-Guided User Simulation (2026.acl-industry)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly deployed as customer-facing agents due to stochastic, multi-turn interactions.
Approach: They propose a snapshot-based, coverage-guided user simulation framework for efficient and systematic exploration of multi-turn agent behavior.
Outcome: Experiments on multi-domain benchmarks show that the proposed method improves failure discovery efficiency and task-level coverage compared to standard linear rollout evaluation without increasing overall cost.
Evaluating Conversational Agents with Persona-driven User Simulations based on Large Language Models: A Sales Bot Case Study (2025.emnlp-industry)

Copied to clipboard

Challenge: Recent advances in LLMs enable sophisticated user simulations that can replace traditional rule-based evaluations.
Approach: They propose a persona-driven approach to conversational agent evaluation using Large Language Models (LLMs) they introduce a dataset of customer personas, which are then used to configure a single LLM-based user simulator.
Outcome: The proposed model emulates nuanced customer roles and can implement cross-selling strategies with minimal impact on customer satisfaction, varying by customer type.
Small Agents, Big Gains: Journey-Aware and Critic-Guided Simulation for Long-Horizon Shopping Dialogues (2026.acl-industry)

Copied to clipboard

Challenge: e-commerce assistants must support inspiration, comparison, and tool-grounded fact-checking . lack of data-coverage and verification problem hampers efficient, deployable models . eaa: "training trajectories must cover diverse user workflows with high fidelity"
Approach: They propose a system that synthesizes diverse, faithful, and policy-aligned shopping trajectories . a small model can significantly outperform same-size baselines and surpass a large-model baseline .
Outcome: The proposed model outperforms existing models and surpasses large models with 8 higher inference throughput.
Persona-Grounded Safety Evaluation of AI Companions in Multi-Turn Conversations (2026.acl-long)

Copied to clipboard

Challenge: Existing safety evaluations rely on self-reported user data or interviews . a recent study evaluated how Replika responds to high-risk user groups .
Approach: They propose a framework for controlled simulation and safety evaluation of multi-turn interactions with AI companion applications.
Outcome: The proposed framework evaluates how Replika responds to high-risk user groups . it incorporates emotion modeling and LLM-assisted utterance-and harm-level classification .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations