paper-with-me

Papers

AgentOrca: A Dual-System Framework to Evaluate Language Agents on Operational Routine and Constraint Adherence

2025-03-11 · Zekun Li, Shinda Huang, Jiangtian Wang, Nathan Zhang, Antonis Antoniades, Wenyue Hua, Kaijie Zhu, Sirui Zeng, William Yang Wang, Xifeng Yan

As language agents progressively automate critical tasks across domains, their ability to operate within operational constraints and safety protocols becomes essential. While extensive research has demonstrated these agents' effectiveness in downstream task completion, their reliability in following operational procedures and constraints remains largely unexplored. To this end, we present AgentOrca, a dual-system framework for evaluating language agents' compliance with operational constraints and routines. Our framework encodes action constraints and routines through both natural language prompts for agents and corresponding executable code serving as ground truth for automated verification. Through an automated pipeline of test case generation and evaluation across five real-world domains, we quantitatively assess current language agents' adherence to operational constraints. Our findings reveal notable performance gaps among state-of-the-art models, with large reasoning models like o1 demonstrating superior compliance while others show significantly lower performance, particularly when encountering complex constraints or user persuasion attempts.

📄 PDF Abstract BibTeX arXiv:2503.08669

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models

2025-11-21 · Xiongtao Sun, Hui Li, Jiaming Zhang, Yujie Yang 외 arxiv

Modern Vision-Language Models (VLMs) pose significant individual-level privacy risks by linking fragmented multimodal data to identifiable individuals through hierarchical chain-of-thought reasoning. However, existing pr…

Speaking in Words, Thinking in Logic: A Dual-Process Framework in QA Systems

2025-07-28 · Tuan Bui, Trong Le, Phat Thai, Sang Nguyen 외 arxiv

Recent advances in large language models (LLMs) have significantly enhanced question-answering (QA) capabilities, particularly in open-domain contexts. However, in closed-domain scenarios such as education, healthcare, a…

Natural Language UnderstandingFormal Logic

A Proposed Large Language Model-Based Smart Search for Archive System

2025-01-13 · Ha Dung Nguyen, Thi-Hoang Anh Nguyen, Thanh Binh Nguyen

This study presents a novel framework for smart search in digital archival systems, leveraging the capabilities of Large Language Models (LLMs) to enhance information retrieval. By employing a Retrieval-Augmented Generat…

Information RetrievalLanguage ModelingLanguage ModellingLarge Language Model+4

Behavior measures are predicted by how information is encoded in an individual's brain

2021-12-11 · Jennifer Williams, Leila Wehbe

Similar to how differences in the proficiency of the cardiovascular and musculoskeletal system predict an individual's athletic ability, differences in how the same brain region encodes information across individuals may…

IMPersona: Evaluating Individual Level LM Impersonation

2025-04-06 · Quan Shi, Carlos E. Jimenez, Stephen Dong, Brian Seo 외

As language models achieve increasingly human-like capabilities in conversational text generation, a critical question emerges: to what extent can these systems simulate the characteristics of specific individuals? To ev…

Text Generation