Get started
Author

Amir Saeidi

Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation
2025 · Neeraj Varshney, Satyam Raj, et al. · 8
PDF
UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs’ Memorization
2025 · Md Nayem Uddin, Amir Saeidi, et al. · Annual Meeting of the Association for Computational Linguistics (ACL) · 4
PDF
Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization
2024 · Saeidi, Amir, Verma, Shivanshu, et al. · arXiv (Cornell University) · 1
PDF
$τ$-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions
2026 · Singh, Rishitosh Kumar, Saeidi, Amir, et al. · arXiv (Cornell University)
PDF
CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents
2026 · Saeidi, Amir, Zhang, Zehua, et al. · arXiv (Cornell University)
PDF
Strategies for Deploying Large Language Models for Ascertaining Clinical Outcomes and Sites of Metastases From Radiology Impressions in Patients With Cancer
2026 · Syed Arsalan Ahmed Naqvi, Irbaz Bin Riaz, et al. · JCO Clinical Cancer Informatics
LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents
2026 · Uddin, Md Nayem, Saeidi, Amir, et al. · arXiv (Cornell University)
PDF
FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments
2026 · Association for Computational Linguistics 2026, Baral, Chitta, et al. · Underline Science Inc.
FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments
2026 · Saeidi, Amir, Mishra, Venkatesh, et al. · arXiv (Cornell University)
FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments
2026 · Saeidi, Amir, Mishra, Venkatesh, et al. · arXiv (Cornell University)
PDF
ML-AutoResearch: Training Machine Learning Research Agents with Automatically Generated Environments
2026 · Cai, Ziyang, Saeidi, Amir, et al. · arXiv (Cornell University)
PDF
FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments
2026 · Amir Saeidi, Venkatesh Mishra, et al.
PDF
Dual Caption Preference Optimization for Diffusion Models
2025 · Saeidi, Amir, Luo, Yiran, et al. · arXiv (Cornell University)
PDF
UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization
2024 · Uddin, Md Nayem, Saeidi, Amir, et al. · arXiv (Cornell University)
PDF
Works count: 16
Citation count: 13
H-index: 2
I10-index:
Year
Topic
Type