DR
Dan Roth
cs.CLcs.AIcs.LGcs.CVcs.IRstat.MLcs.DBcs.HCcs.SEEpilepsy
On Valency
published · living versionsW_eyfwvjt7·v1 · currentpublished
Prefix Executability: Evaluating Tool-Using Agents Beyond Final Success
with Amir H. Rezaeian, Weiyi Sun, Yassine Benajiba
1 version
W_jcrhtzgt·v1published
W_r6xkyhyj·v1published
Preprints & journals
269 papers in the corpus · 1996–2026Ask Less, Ask Better: Allocating User Attention in Proactive LLM Agents with Interruption Budgets2610.24411v1 · Xuanming Zhang, Amir H. Rezaeian, Miguel Ballesteros et al.2026 · 0 citationsarXivon Valency
Same Context, Different Agents: A Behavioral Study of Semantic Layers, Multi-Agent Orchestration and Memory Compaction in Data Agents2610.20959v2 · Zhivar Sourati, Marianne Menglin Liu, Zheng Wang et al.2026 · 0 citationsarXiv
VELD-QA: A Large-Scale Dataset for Visual Evidence Grounding and Question Answering in Long Documents2610.20964v2 · Zhivar Sourati, Marianne Menglin Liu, Rongguang Wang et al.2026 · 0 citationsarXiv
ExperienceIndex: Artifact-Grounded Memory2610.10091v1 · Peter Baile Chen, Geoffrey X. Yu, Xinming Liu et al.2026 · 0 citationsarXiv
From Portraits to Pathology: Probing Diagnostic Overreach in Vision-Language Models2609.05540v2 · Karan Dua, Amit Agarwal, Hitesh Laxmichand Patel et al.2026 · 0 citationsarXiv
From Solver Feedback to Faithful Plans: Multi-Role Reinforcement Learning for Symbolic Planning2608.21897v2 · Chenghao Zhang, Yikai Mao, Haoyu Gao et al.2026 · 0 citationsarXiv
Training Needs Trustworthy Worlds: Verified Synthetic Web Environments for Agent Learning2608.21898v2 · Chenghao Zhang, Yuxi Cheng, Saisai Hu et al.2026 · 0 citationsarXiv
PLSQLBench: Benchmarking LLM Systems for Executable Procedural Database Programming2608.15931v1 · Marianne Menglin Liu, Leonid Boytsov, Daniel W. Peterson et al.2026 · 0 citationsarXiv
PersonaMem-v3: Toward Omni-Platform Personal Intelligence for Holistic User Understanding, Recommendation, and Agentic Tasks2608.21381v2 · Bowen Jiang, Yuan Yuan, Zhuoqun Hao et al.2026 · 0 citationsarXiv
Is Code Better Than Language for Algorithmic Reasoning2606.15589v1 · Terry Tong, Yu Feng, Surbhi Goel et al.2026 · 0 citationsarXiv
SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probing2606.11424v1 · Sai Ashish Somayajula, Marianne Menglin Liu, Chuan Lei et al.2026 · 0 citationsarXiv
Do Image-Text Metrics Respect Semantic Invariances?2605.24702v1 · Amit Agarwal, Hitesh Laxmichand Patel, Meizhu Liu et al.2026 · 0 citationsarXiv
GSM-SEM: Benchmark and Framework for Generating Semantically Variant Augmentations2605.07053v2 · Jyotika Singh, Fang Tu, Aziza Mirsaidova et al.2026 · 0 citationsarXiv
Robust Audio-Text Retrieval via Cross-Modal Attention and Hybrid Loss2604.23323v1 · Meizhu Liu, Matthew Rowe, Amit Agarwal et al.2026 · 0 citationsarXiv
When Vision-Language Models Judge Without Seeing: Exposing Informativeness Bias2604.17768v1 · Xiaohan Zou, Roshan Sridhar, Mohammadtaher Safarzadeh et al.2026 · 1 citationarXiv
SPENCE: A Syntactic Probe for Detecting Contamination in NL2SQL Benchmarks2604.17771v1 · Mohammadtaher Safarzadeh, Hitesh Laxmichand Patel, Afshin Orojlooyjadid et al.2026 · 0 citationsarXiv
JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents2604.19821v1 · Sandip Ghoshal, Anshul Mittal, Jyotika Singh et al.2026 · 0 citationsFindings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026
MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation2604.08782v3 · Jyotika Singh, Fang Tu, Miguel Ballesteros et al.2026 · 0 citationsarXiv
DiffuMask: Diffusion Language Model for Token-level Prompt Pruning2604.06627v1 · Caleb Zheng, Jyotika Singh, Fang Tu et al.2026 · 0 citationsarXiv
PAR-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering2603.29085v1 · Xingyu Li, Rongguang Wang, Yuying Wang et al.2026 · 0 citationsarXiv
GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation2603.24925v3 · Ruizhong Miao, Yuying Wang, Rongguang Wang et al.2026 · 0 citationsarXiv
DataProphet: Demystifying Supervision Data Generalization in Multimodal LLMs2603.19688v1 · Xuan Qi, Luxi He, Dan Roth et al.2026 · 0 citationsarXiv
LLM NL2SQL Robustness: Surface Noise vs. Linguistic Variation in Traditional and Agentic Settings2603.17017v1 · Lifu Tu, Rongguang Wang, Tao Sheng et al.2026 · 0 citationsarXiv
Think Twice Before You Write -- an Entropy-based Decoding Strategy to Enhance LLM Reasoning2604.00018v1 · Jiashu He, Meizhu Liu, Olaitan P Olaleye et al.2026 · 0 citationsarXiv
Chart-RL: Generalized Chart Comprehension via Reinforcement Learning with Verifiable Rewards2603.06958v1 · Xin Zhang, Xingyu Li, Rongguang Wang et al.2026 · 0 citationsarXiv
AI+HW 2035: Shaping the Next Decade2603.05225v1 · Deming Chen, Jason Cong, Azalia Mirhoseini et al.2026 · 0 citationsarXiv
SAGE: Structure Aware Graph Expansion for Retrieval of Heterogeneous Data2602.16964v1 · Prasham Titiya, Rohit Khoja, Tomer Wolfson et al.2026 · 0 citationsarXiv
On Improving Neurosymbolic Learning by Exploiting the Representation Space2602.07973v1 · Aaditya Naik, Efthymia Tsamoura, Shibo Jin et al.2026 · 0 citationsarXiv
Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"2602.04853v2 · Dhruv Madhwal, Lyuxin David Zhang, Dan Roth et al.2026 · 0 citationsarXiv
CORE-T: COherent REtrieval of Tables for Text-to-SQL2601.13111v3 · Hassan Soliman, Vivek Gupta, Dan Roth et al.2026 · 0 citationsProceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026), pp. 2082-2114, Association for Computational Linguistics, 2026
Comparative effectiveness of anti-seizure medications in emulated trials using medical informatics.40663627 · Xie, Kevin, Korzun, Jacob, Zhou, Daniel J et al.2025 · 4 citationsBrain : a journal of neurology. 2025;148(12):4288-4298
Can LLMs Narrate Tabular Data? An Evaluation Framework for Natural Language Representations of Text-to-SQL System Outputs2510.23854v1 · Jyotika Singh, Weiyi Sun, Amit Agarwal et al.2025 · 0 citationsarXiv
OraPlan-SQL: A Planning-Centric Framework for Complex Bilingual NL2SQL Reasoning2510.23870v1 · Marianne Menglin Liu, Sai Ashish Somayajula, Syed Fahad Allam Shah et al.2025 · 0 citationsarXiv
RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts2510.05310v1 · Yining She, Daniel W. Peterson, Marianne Menglin Liu et al.2025 · 0 citationsarXiv
Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks2510.02286v2 · Ruohao Guo, Afshin Oroojlooy, Roshan Sridhar et al.2025 · 0 citationsarXiv
Aligning LLMs for Multilingual Consistency in Enterprise Applications2509.23659v2 · Amit Agarwal, Hansa Meghwani, Hitesh Laxmichand Patel et al.2025 · 0 citationsarXiv
RCI: A Score for Evaluating Global and Local Reasoning in Multimodal Benchmarks2509.23673v1 · Amit Agarwal, Hitesh Laxmichand Patel, Srikant Panda et al.2025 · 0 citationsarXiv
PCRI: Measuring Context Robustness in Multimodal Models for Enterprise Applications2509.23879v1 · Hitesh Laxmichand Patel, Amit Agarwal, Srikant Panda et al.2025 · 0 citationsarXiv
Evaluating NL2SQL via SQL2NL2509.04657v1 · Mohammadtaher Safarzadeh, Afshin Oroojlooyjadid, Dan Roth2025 · 5 citationsarXiv
Reasoning is about giving reasons2508.14488v1 · Krunal Shah, Dan Roth2025 · 0 citationsarXiv
A Community-driven vision for a new Knowledge Resource for AI2506.16596v3 · Vinay K Chaudhri, Chaitan Baru, Brandon Bennett et al.2025 · 0 citationsarXiv
PRAISE: Enhancing Product Descriptions with LLM-Driven Structured Insights2506.17314v1 · Adnan Qidwai, Srija Mukhopadhyay, Prerana Khatiwada et al.2025 · 1 citationarXiv
No Universal Prompt: Unifying Reasoning through Adaptive Prompting for Temporal Table Reasoning2506.11246v2 · Abhishek Rajgaria, Kushagra Dixit, Mayank Vyas et al.2025 · 0 citationsarXiv
LLM-Symbolic Integration for Robust Temporal Tabular Reasoning2506.05746v1 · Atharv Kulkarni, Kushagra Dixit, Vivek Srikumar et al.2025 · 0 citationsarXiv
AUTOCT: Automating Interpretable Clinical Trial Prediction with LLM Agents2506.04293v1 · Fengze Liu, Haoyu Wang, Joonhyuk Cho et al.2025 · 4 citationsarXiv
LogiCoL: Logically-Informed Contrastive Learning for Set-based Dense Retrieval2505.19588v1 · Yanzhen Shen, Sihao Chen, Xueqiang Xu et al.2025 · 2 citationsarXiv
Weaver: Interweaving SQL and LLM for Table Reasoning2505.18961v2 · Rohit Khoja, Devanshu Gupta, Yanjie Fu et al.2025 · 2 citationsarXiv
UNJOIN: Enhancing Multi-Table Text-to-SQL Generation via Schema Simplification2505.18122v1 · Poojah Ganesan, Rajat Aayush Jha, Dan Roth et al.2025 · 1 citationarXiv
SAKE: Structured Agentic Knowledge Extrapolation for Complex LLM Reasoning via Reinforcement Learning2505.15062v6 · Jiashu He, Jinxuan Fan, Bowen Jiang et al.2025 · 0 citationsarXiv
Zero-Shot Extraction of Seizure Outcomes from Clinical Notes Using Generative Pretrained Transformers.40726746 · Ojemann, William K S, Xie, Kevin, Liu, Kevin et al.2026 · 9 citationsJournal of healthcare informatics research. 2025;9(3):380-400
Career total: 724 works. 269 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.