Papers with LLM-powered agents
MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models (2025.emnlp-demos)
Copied to clipboard
Zhiwei Liu, Jielin Qiu, Shiyu Wang, Jianguo Zhang, Zuxin Liu, Roshan Ram, Haolin Chen, Weiran Yao, Shelby Heinecke, Silvio Savarese, Huan Wang, Caiming Xiong
| Challenge: | Existing evaluation frameworks suffer from limitations such as static task benchmarks, limited scope, and inadequate integration with practical applications. |
| Approach: | They propose an open-source, Model Context Protocol-based evaluation framework specifically tailored for comprehensive and systematic assessment of LLM-powered agents. |
| Outcome: | The proposed framework uncovers nuanced performance patterns and identify domain-specific strengths and weaknesses, providing valuable insights beyond traditional binary success metrics. |
Banking Done Right: Redefining Retail Banking with Language-Centric AI (2025.emnlp-industry)
Copied to clipboard
Xin Jie Chua, Jeraelyn Ming Li Tan, Jia Xuan Tan, Soon Chang Poh, Yi Xian Goh, Debbie Hui Tian Choong, Foong Chee Mun, Sze Jue Yang, Chee Seng Chan
| Challenge: | This is the first global regulator-approved deployment where conversational AI functions as the primary banking interface. |
| Approach: | They propose a framework that powers a conversational AI framework that is powered by a closed-source LLM developed internally and replaces rigid multi-screen workflows with a single dialogue orchestrated by four LLM-powered agents. |
| Outcome: | The proposed framework replaces multi-screen workflows with a single dialogue orchestrated by four LLM-powered agents (Guardrails, Intent, Payment, and FAQ). |
Foundations of PEERS: Assessing LLM Role Performance in Educational Simulations (2025.acl-srw)
Copied to clipboard
Jasper Meynard Arana, Kristine Ann M. Carandang, Ethan Robert Casin, Christian Alis, Daniel Stanley Tan, Erika Fille Legara, Christopher Monterola
| Challenge: | In education, peer instruction is widely recognized as an effective active learning strategy, but evaluations of PI are limited by logistical constraints and variability in classroom settings. |
| Approach: | They propose a simulation framework that integrates Agent-Based Modeling, Large Language Models, and Bayesian Knowledge Tracing to emulate student learning dynamics. |
| Outcome: | The proposed framework integrates Agent-Based Modeling, Large Language Models, and Bayesian Knowledge Tracing to emulate student learning dynamics in real classrooms. |
Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are evolving rapidly and require manual evaluations. |
| Approach: | They propose an LLM-powered framework that automates the entire evaluation process using LLM agents. |
| Outcome: | The proposed framework shows a 92.14% correlation with human preferences, surpassing all previous expert-annotated benchmarks without any manual efforts. |
Beyond Words: Integrating Theory of Mind into Conversational Agents for Human-Like Belief, Desire, and Intention Alignment (2025.findings-acl)
Copied to clipboard
| Challenge: | Empirical evaluations of LLaMA-3 models demonstrate that ToM-informed alignment improves response quality, achieving win rates of 63% and 67%, respectively. |
| Approach: | They investigate whether open-source LLaMA models can represent and retain ToM-related constructs and whether they can be used to generate more aligned responses. |
| Outcome: | The proposed models can represent and retain ToM-related constructs and improve response quality. |
AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models (2024.findings-emnlp)
Copied to clipboard
Jiale Cheng, Yida Lu, Xiaotao Gu, Pei Ke, Xiao Liu, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang
| Challenge: | Large Language Models (LLMs) exhibit significant but subtle weaknesses, such as mistakes in instruction-following or coding tasks. |
| Approach: | They propose a framework to automatically expose weaknesses in Large Language Models (LLMs) they use three LLM-powered agents to perform comprehensive weakness identification . |
| Outcome: | The proposed framework shows that it is more effective than untargeted data augmentation methods like Self-Instruct to identify weaknesses in LLMs. |
On the Multi-turn Instruction Following for Conversational Web Agents (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable abilities in planning and executing multi-step interactions within web-based environments. |
| Approach: | They propose a framework for conversational web navigation that uses multi-turn interactions with both the user and the environment. |
| Outcome: | The proposed framework is based on a multi-turn Mind2Web (MT-Mind2Web) it is designed to perform multi-step interactions with web-based environments . |
Ask-before-Plan: Proactive Language Agents for Real-World Planning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | despite the advancements of large language models, the potential of LLM-powered agents to comprehend ambiguous user instructions is still under exploration. |
| Approach: | They propose a task that requires agents to predict clarification needs based on conversation and agentenvironment interaction and generate a plan to fulfill the user's demands. |
| Outcome: | The proposed framework is based on a new ask-before-plan benchmark dataset. |
Salespeople vs SalesBot: Exploring the Role of Educational Value in Conversational Recommender Systems (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing conversational recommender systems focus on a single-shot approach to understand user preferences and provide recommendations. |
| Approach: | They propose a problem space for conversational agents that aim to provide both product recommendations and educational value through mixed-type mixed-initiative dialog. |
| Outcome: | The proposed framework can simulate salesbot and shopperbot agents and provide both product recommendations and educational value through mixed-type mixed-initiative dialog. |
GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities (2026.acl-long)
Copied to clipboard
Diganta Misra, Nizar Islah, Victor May, Brice Rauby, Zihan Wang, Justine Gehring, Antonio Orvieto, Muawiz Sajjad Chaudhary, Eilif B. Muller, Irina Rish, Samira Ebrahimi Kahou, Massimo Caccia
| Challenge: | Existing code evolution benchmarks lack execution-based evaluation for generating code compliant with specific library versions. |
| Approach: | They propose a new Python code completion problem that evaluates the ability of large language models to perform version-conditioned code generation. |
| Outcome: | The proposed benchmarks show that state-of-the-art systems can perform version-conditioned code generation with high success rates. |