llm agent

ALRPHFS: Adversarially Learned Risk Patterns with Hierarchical Fast & Slow Reasoning for Robust Agent Defense EMNLP 2025 ALYMPICS: LLM Agents Meet Game Theory COLING 2025 AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering EMNLP 2025 AutoClean: LLMs Can Prepare Their Training Corpus NAACL 2025 Automated Hypothesis Validation with Agentic Sequential Falsifications ICML 2025 AutoPDL: Automatic Prompt Optimization for LLM Agents AutoML 2025 AutoPenBench: A Vulnerability Testing Benchmark for Generative Agents EMNLP 2025 AutoQual: An LLM Agent for Automated Discovery of Interpretable Features for Review Quality Assessment EMNLP 2025 Benchmarking LLMs and LLM-based Agents in Practical Vulnerability Detection for Code Repositories ACL 2025 Beyond Frameworks: Unpacking Collaboration Strategies in Multi-Agent Systems ACL 2025 Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In NAACL 2025 Can LLMs Help You at Work? A Sandbox for Evaluating LLM Agents in Enterprise Environments EMNLP 2025 Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions ACL 2025 CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space EMNLP 2025 CompileAgent: Automated Real-World Repo-Level Compilation with Tool-Integrated LLM-based Agent System ACL 2025 CourtReasoner: Can LLM Agents Reason Like Judges? EMNLP 2025 CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments NAACL 2025 CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositories NAACL 2025 CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities ICML 2025 CVE-Bench: Benchmarking LLM-based Software Engineering Agent’s Ability to Repair Real-World CVE Vulnerabilities NAACL 2025 Data Interpreter: An LLM Agent for Data Science ACL 2025 DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automation EMNLP 2025 DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent EMNLP 2025 Divergent Thoughts toward One Goal: LLM-based Multi-Agent Collaboration System for Electronic Design Automation NAACL 2025 Divide, Optimize, Merge: Scalable Fine-Grained Generative Optimization for LLM Agents EMNLP 2025