KP
Kishan Panaganti
cs.LGcs.AIstat.MLcs.CLcs.GTcs.MAcs.SYeess.SYcs.CVcs.IR
On Valency
published · living versionsW_2k43zt4z·v1 · currentpublished
More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents
with Ruhan Wang, Dongruo Zhou
1 version
Preprints & journals
31 papers in the corpus · 2020–2026More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents2610.27406v1 · Ruhan Wang, Kishan Panaganti, Dongruo Zhou2026 · 0 citationsarXivon Valency
Online Robust Reinforcement Learning Through Monte-Carlo Planning2609.18599v1 · Tuan Dam, Kishan Panaganti, Brahim Driss et al.2026 · 0 citationsarXiv
FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience2609.03241v1 · Zixun Huang, Kishan Panaganti, Haitao Mi et al.2026 · 0 citationsarXiv
Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning2607.18722v3 · Junyao Yang, Yucheng Shi, Zongxia Li et al.2026 · 0 citationsarXiv
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable2607.13285v1 · Ruhan Wang, Yucheng Shi, Zongxia Li et al.2026 · 0 citationsarXiv
Leveraging Machine-Learned Advice in Strategic Interactions with No-Regret Learners2606.10261v1 · Tinashe Handina, Tongxin Li, Kishan Panaganti et al.2026 · 0 citationsarXiv
Reasoning or Memorization? Direction-Aware Diversity Exploration in LLM Reinforcement Learning2606.10346v1 · Jiangnan Xia, Yucheng Shi, Yu Yang et al.2026 · 0 citationsarXiv
Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis2605.14392v1 · Yucheng Shi, Zhenwen Liang, Kishan Panaganti et al.2026 · 0 citationsarXiv
Distributionally Robust Cooperative Multi-Agent Reinforcement Learning via Robust Value Factorization2602.11437v1 · Chengrui Qu, Christopher Yeh, Kishan Panaganti et al.2026 · 0 citationsarXiv
The Single-Multi Evolution Loop for Self-Improving Model Collaboration Systems2602.05182v2 · Shangbin Feng, Kishan Panaganti, Yulia Tsvetkov et al.2026 · 0 citationsarXiv
Group Distributionally Robust Optimization-Driven Reinforcement Learning for LLM Reasoning2601.19280v1 · Kishan Panaganti, Zhenwen Liang, Wenhao Yu et al.2026 · 0 citationsarXiv
Guided Self-Evolving LLMs with Minimal Human Supervision2512.02472v1 · Wenhao Yu, Zhenwen Liang, Chengsong Huang et al.2025 · 0 citationsarXiv
Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values2510.20187v1 · Dian Yu, Yulai Zhao, Kishan Panaganti et al.2025 · 0 citationsarXiv
Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation2509.15194v4 · Yujun Zhou, Zhenwen Liang, Haolin Liu et al.2025 · 0 citationsarXiv
Risk-Averse Total-Reward Reinforcement Learning2506.21683v2 · Xihong Su, Jia Lin Hau, Gersi Doko et al.2025 · 0 citationsarXiv
TARDIS STRIDE: A Spatio-Temporal Road Image Dataset and World Model for Autonomy2506.11302v3 · H'ector Carri'on, Yutong Bai, V'ictor A. Hern'andez Castro et al.2025 · 0 citationsarXiv
Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees2505.19238v3 · Sourav Ganguly, Kishan Panaganti, Arnob Ghosh et al.2025 · 0 citationsarXiv
KL-regularization Itself is Differentially Private in Bandits and RLHF2505.18407v2 · Yizhou Zhang, Kishan Panaganti, Laixi Shi et al.2025 · 0 citationsarXiv
Robust LLM Alignment via Distributionally Robust Direct Preference Optimization2502.01930v4 · Zaiyan Xu, Sushil Vemuri, Kishan Panaganti et al.2025 · 1 citationarXiv
Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data2411.03810v1 · Chengrui Qu, Laixi Shi, Kishan Panaganti et al.2024 · 0 citationsarXiv
Distributionally Robust Constrained Reinforcement Learning under Strong Duality2406.15788v1 · Zhengfei Zhang, Kishan Panaganti, Laixi Shi et al.2024 · 0 citationsarXiv
Tractable Equilibrium Computation in Markov Games through Risk Aversion2406.14156v2 · Eric Mazumdar, Kishan Panaganti, Laixi Shi2024 · 0 citationsarXiv
Model-Free Robust -Divergence Reinforcement Learning Using Both Offline and Online Data2405.05468v1 · Kishan Panaganti, Adam Wierman, Eric Mazumdar2024 · 0 citationsarXiv
Bridging Distributionally Robust Learning and Offline RL: An Approach to Mitigate Distribution Shift and Partial Data Coverage2310.18434v1 · Kishan Panaganti, Zaiyan Xu, Dileep Kalathil et al.2023 · 0 citationsarXiv
Improved Sample Complexity Bounds for Distributionally Robust Reinforcement Learning2303.02783v2 · Zaiyan Xu, Kishan Panaganti, Dileep Kalathil2023 · 3 citationsProceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR 206:9728-9754, 2023
Personalized Reward Learning with Interaction-Grounded Learning (IGL)2211.15823v2 · Jessica Maghakian, Paul Mineiro, Kishan Panaganti et al.2022 · 0 citationsarXiv
Robust Reinforcement Learning using Offline Data2208.05129v2 · Kishan Panaganti, Zaiyan Xu, Dileep Kalathil et al.2022 · 23 citationsarXiv
Off-Policy Evaluation Using Information Borrowing and Context-Based Switching2112.09865v2 · Sutanoy Dasgupta, Yabo Niu, Kishan Panaganti et al.2021 · 0 citationsarXiv
Sample Complexity of Robust Reinforcement Learning with a Generative Model2112.01506v3 · Kishan Panaganti, Dileep Kalathil2021 · 13 citationsarXiv
Robust Reinforcement Learning using Least Squares Policy Iteration with Provable Performance Guarantees2006.11608v4 · Kishan Panaganti, Dileep Kalathil2020 · 16 citationsarXiv
Bounded Regret for Finitely Parameterized Multi-Armed Bandits2003.01328v5 · Kishan Panaganti, Dileep Kalathil2020 · 2 citationsarXiv
Career total: 37 works. 31 are in this corpus.
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.