TP
Tomas Pfister
cs.LGcs.CLcs.AIcs.CVstat.MLcs.MAcs.CRcs.IRcs.SEcs.DB
On Valency
published · living versionsW_hatarq3r·v1 · currentpublished
W_cf2dagf8·v1published
W_eyupgefd·v2published
Preprints & journals
127 papers in the corpus · 2015–2026Object-Oriented Harness: Evolving Agent Harnesses through Object-Oriented Design2610.28380v1 · Gaotang Li, Bhavana Dalvi Mishra, Yifei Ming et al.2026 · 0 citationsarXivon Valency
WhatIf-Bench: Benchmarking Intervention-Aware Time Series Forecasting2610.26582v2 · Arjun Ashok, Mihir Parmar, Palash Goyal et al.2026 · 0 citationsarXivon Valency
DuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation Bottleneck2610.17184v1 · Shubham Agarwal, Akshat Gupta, Mike Heddes et al.2026 · 0 citationsarXiv
Harmony Harness: Multi-Objective Self-Evolution of Agent Harnesses2610.15150v1 · Weichen Yu, Lesly Miculicich, Bhavana Dalvi Mishra et al.2026 · 0 citationsarXiv
Harness^2: Recursive Agent Harnessing for an Open World2610.14224v1 · Ruiyao Xu, Yanfei Chen, Zhongying CuiZhu et al.2026 · 1 citationarXiv
VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails2610.12813v1 · Duy Nguyen, Lesly Miculicich, Bhavana Dalvi Mishra et al.2026 · 0 citationsarXiv
VIS-Ground: Video Interactive Storytelling with Contextual Grounding2610.09326v2 · Bingxuan Li, Yiwen Song, Xueqing Wu et al.2026 · 0 citationsarXiv
SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting2610.04109v1 · Mingtian Tan, Palash Goyal, Mihir Parmar et al.2026 · 0 citationsarXiv
AIM: Agentic Idea Management for Automated Research2609.38445v1 · Hyeong Kyu Choi, Bhavana Dalvi Mishra, Jiefeng Chen et al.2026 · 0 citationsarXiv
PreviewDiff: Multimodal Critic-Guided Search over Diffusion Latents2609.36199v1 · Vighnesh Subramaniam, Boris Katz, Brian Cheung et al.2026 · 0 citationsarXiv
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses2609.24972v3 · Peng Xia, Rujun Han, Zifeng Wang et al.2026 · 0 citationsarXiv
ScientistTwo: Pioneering the Human Knowledge Frontier with Autonomous AI2609.19644v1 · Jaehyun Nam, Jinsung Yoon, Yanzhou Pan et al.2026 · 0 citationsarXiv
PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback2608.30241v1 · Xueqing Wu, Ashwin Balasubramanian, Bingxuan Li et al.2026 · 0 citationsarXiv
EnvHarness: Awakening Static Worlds for Agent Learning2608.19880v1 · Chengsong Huang, Zifeng Wang, Rujun Han et al.2026 · 0 citationsarXiv
The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust2606.07822v2 · Nishant Subramani, Palash Goyal, Yiwen Song et al.2026 · 0 citationsarXiv
T2J-BENCH: Benchmarking Coding Agents on Execution-Grounded PyTorch-to-JAX Repository Migration2605.29054v3 · Tao Feng, Jiefeng Chen, Linxin Song et al.2026 · 0 citationsarXiv
Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems2605.23109v1 · Shubham Agarwal, Alexander Krentsel, Shu Liu et al.2026 · 0 citationsarXiv
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards2605.10899v2 · Gaotang Li, Bhavana Dalvi Mishra, Zifeng Wang et al.2026 · 0 citationsarXiv
STRIDE: Reasoning-Aware Training for Time Series Forecasting2605.08625v2 · Md Atik Ahamed, Mihir Parmar, Palash Goyal et al.2026 · 0 citationsarXiv
SkillOS: Learning Skill Curation for Self-Evolving Agents2605.06614v1 · Siru Ouyang, Jun Yan, Yanfei Chen et al.2026 · 0 citationsarXiv
ARD: Agentic Autoregressive Diffusion for Long Video Consistency2605.06924v1 · Do Xuan Long, Yale Song, Min-Yen Kan et al.2026 · 0 citationsarXiv
Co-Director: Agentic Generative Video Storytelling2604.24842v1 · Yale Song, Yiwen Song, Nick Losier et al.2026 · 0 citationsarXiv
MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models2604.23321v2 · Haohang Huang, Xuan Lu, Mingyi Su et al.2026 · 0 citationsarXiv
CANVAS: Continuity-Aware Narratives via Visual Agentic Storyboarding2604.13452v1 · Ishani Mondal, Yiwen Song, Mihir Parmar et al.2026 · 0 citationsarXiv
VQQA: An Agentic Approach for Video Evaluation and Quality Improvement2603.12310v1 · Yiwen Song, Tomas Pfister, Yale Song2026 · 0 citationsarXiv
Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents2602.02164v2 · Pengfei He, Ash Fox, Lesly Miculicich et al.2026 · 0 citationsarXiv
MARS: Modular Agent with Reflective Search for Automated AI Research2602.02660v3 · Jiefeng Chen, Bhavana Dalvi Mishra, Jaehyun Nam et al.2026 · 0 citationsarXiv
ScholarPeer: A Context-Aware Multi-Agent Framework for Automated Peer Review2601.22638v2 · Palash Goyal, Mihir Parmar, Yiwen Song et al.2026 · 0 citationsarXiv
PaperBanana: Automating Academic Illustration for AI Scientists2601.23265v2 · Dawei Zhu, Rui Meng, Yale Song et al.2026 · 1 citationarXiv
SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback2601.18202v1 · Fangyuan Xu, Rujun Han, Yanfei Chen et al.2026 · 0 citationsarXiv
Budget-Aware Tool Use Enables Effective Agent Scaling2511.17006v2 · Tengxiao Liu, Zifeng Wang, Jin Miao et al.2025 · 1 citationarXiv
DocLens : A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding2511.11552v1 · Dawei Zhu, Rui Meng, Jiefeng Chen et al.2025 · 2 citationsarXiv
VISTA: A Test-Time Self-Improving Video Generation Agent2510.15831v1 · Do Xuan Long, Xingchen Wan, Hootan Nakhost et al.2025 · 0 citationsarXiv
CoDA: Agentic Systems for Collaborative Data Visualization2510.03194v1 · Zichen Chen, Jiefeng Chen, Sercan O. Arik et al.2025 · 0 citationsarXiv
VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation2510.05156v1 · Lesly Miculicich, Mihir Parmar, Hamid Palangi et al.2025 · 2 citationsarXiv
TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture2510.01279v1 · Yongchao Chen, Jiefeng Chen, Rui Meng et al.2025 · 0 citationsarXiv
LLM-Based Multi-Agent Blackboard System for Information Discovery in Data Science2510.01285v2 · Alireza Salemi, Mihir Parmar, Palash Goyal et al.2025 · 2 citationsarXiv
ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory2509.25140v2 · Siru Ouyang, Jun Yan, I-Hung Hsu et al.2025 · 1 citationarXiv
ATLAS: Constraints-Aware Multi-Agent Collaboration for Real-World Travel Planning2509.25586v1 · Jihye Choi, Jinsung Yoon, Jiefeng Chen et al.2025 · 0 citationsarXiv
HEART: Emotionally-Driven Test-Time Scaling of Language Models2509.22876v6 · Gabriela Pinto, Palash Goyal, Mihir Parmar et al.2025 · 0 citationsarXiv
Deep Researcher with Test-Time Diffusion2507.16075v1 · Rujun Han, Yanfei Chen, Zoey CuiZhu et al.2025 · 1 citationarXiv
On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows2504.01931v4 · Souradip Chakraborty, Mohammadreza Pourreza, Ruoxi Sun et al.2025 · 0 citationsarXiv
In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents2503.08026v2 · Zhen Tan, Jun Yan, I-Hung Hsu et al.2025 · 17 citationsarXiv
Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translation2503.07826v1 · Fan Yin, Zifeng Wang, I-Hung Hsu et al.2025 · 2 citationsarXiv
When One LLM Drools, Multi-LLM Collaboration Rules2502.04506v1 · Shangbin Feng, Wenxuan Ding, Alisa Liu et al.2025 · 1 citationarXiv
Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems2502.04510v2 · Shangbin Feng, Zifeng Wang, Palash Goyal et al.2025 · 0 citationsarXiv
Reverse Thinking Makes LLMs Stronger Reasoners2411.19865v2 · Justin Chih-Yao Chen, Zifeng Wang, Hamid Palangi et al.2024 · 4 citationsarXiv
Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence2410.11163v2 · Shangbin Feng, Zifeng Wang, Yike Wang et al.2024 · 2 citationsarXiv
Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling2410.11325v3 · Wenda Xu, Rujun Han, Zifeng Wang et al.2024 · 2 citationsarXiv
TableRAG: Million-Token Table Understanding with Language Models2410.04739v3 · Si-An Chen, Lesly Miculicich, Julian Martin Eisenschlos et al.2024 · 20 citationsarXiv
Career total: 161 works. 127 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.