AS
Adith Swaminathan
cs.LGcs.AIstat.MLcs.CLcs.IRcs.CRcs.FLcs.NEcs.ROcs.SE
On Valency
published · living versionsW_ec4xva75·v1 · currentpublished
AT-AT: Automatic Tool Optimization from Agent Traces
with Maya Ravichandran, Pragya Tripathi, Dharamendra Kumar, Nathan Kallus
1 version
W_6czxdnsj·v1published
W_n5w52yug·v1published
Preprints & journals
30 papers in the corpus · 2015–2026The Context Gathering Decision Process: A POMDP Framework for Agentic Search2605.07042v1 · Chinmaya Kausik, Adith Swaminathan, Nathan Kallus2026 · 0 citationsarXiv
Understanding the Challenges in Iterative Generative Optimization with LLMs2603.23994v2 · Allen Nie, Xavier Daull, Zhiyi Kuang et al.2026 · 0 citationsarXiv
Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs2602.02909v2 · Kiran Tomlinson, Tobias Schnabel, Adith Swaminathan et al.2026 · 0 citationsarXiv
Formalizing Learning from Language Feedback with Provable Guarantees2506.10341v2 · Wanqiao Xu, Allen Nie, Ruijie Zheng et al.2025 · 0 citationsarXiv
A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMs2505.23816v2 · Trenton Chang, Tobias Schnabel, Adith Swaminathan et al.2025 · 1 citationarXiv
Lost in Transmission: When and Why LLMs Fail to Reason Globally2505.08140v5 · Tobias Schnabel, Kiran Tomlinson, Adith Swaminathan et al.2025 · 0 citationsarXiv
Combining Open-box Simulation and Importance Sampling for Tuning Large-Scale Recommenders2410.03697v1 · Kaushal Paneri, Michael Munje, Kailash Singh Maurya et al.2024 · 0 citationsarXiv
How to Solve Contextual Goal-Oriented Problems with Offline Datasets?2408.07753v2 · Ying Fan, Jingling Li, Adith Swaminathan et al.2024 · 0 citationsarXiv
Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs2406.16218v2 · Ching-An Cheng, Allen Nie, Adith Swaminathan2024 · 4 citationsarXiv
On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots2406.01633v1 · Christine Herlihy, Jennifer Neville, Tobias Schnabel et al.2024 · 1 citationarXiv
The Importance of Directional Feedback for LLM-based Optimizers2405.16434v2 · Allen Nie, Ching-An Cheng, Andrey Kolobov et al.2024 · 3 citationsarXiv
AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks2403.01038v1 · Jiacen Xu, Jack W. Stokes, Geoff McDonald et al.2024 · 23 citationsarXiv
LLF-Bench: Benchmark for Interactive Learning from Language Feedback2312.06853v2 · Ching-An Cheng, Andrey Kolobov, Dipendra Misra et al.2023 · 1 citationarXiv
Interactive Robot Learning from Verbal Correction2310.17555v1 · Huihan Liu, Alice Chen, Yuke Zhu et al.2023 · 2 citationsarXiv
Heuristic-Guided Reinforcement Learning2106.02757v2 · Ching-An Cheng, Andrey Kolobov, Adith Swaminathan2021 · 21 citationsarXiv
Improving Long-Term Metrics in Recommendation Systems using Short-Horizon Reinforcement Learning2106.00589v2 · Bogdan Mazoure, Paul Mineiro, Pavithra Srinath et al.2021 · 2 citationsarXiv
Provably Good Batch Reinforcement Learning Without Great Exploration2007.08202v2 · Yao Liu, Adith Swaminathan, Alekh Agarwal et al.2020 · 35 citationsarXiv
Improved Image Wasserstein Attacks and Defenses2004.12478v2 · Edward J. Hu, Adith Swaminathan, Hadi Salman et al.2020 · 8 citationsarXiv
Working Memory Graphs1911.07141v4 · Ricky Loynd, Roland Fernandez, Asli Celikyilmaz et al.2019 · 8 citationsarXiv
Learning Calibratable Policies using Programmatic Style-Consistency1910.01179v3 · Eric Zhan, Albert Tseng, Yisong Yue et al.2019 · 7 citationsarXiv
Metareasoning in Modular Software Systems: On-the-Fly Configuration using Reinforcement Learning with Rich Contextual Representations1905.05179v1 · Aditya Modi, Debadeepta Dey, Alekh Agarwal et al.2019 · 1 citationarXiv
Off-Policy Policy Gradient with State Distribution Correction1904.08473v2 · Yao Liu, Adith Swaminathan, Alekh Agarwal et al.2019 · 54 citationsarXivon Valency
Multi-Preference Actor Critic1904.03295v1 · Ishan Durugkar, Matthew Hausknecht, Adith Swaminathan et al.2019 · 1 citationarXiv
NAIL: A General Interactive Fiction Agent1902.04259v2 · Matthew Hausknecht, Ricky Loynd, Greg Yang et al.2019 · 24 citationsarXiv
Large-scale Validation of Counterfactual Learning Methods: A Test-Bed1612.00367v2 · Damien Lefortier, Adith Swaminathan, Xiaotao Gu et al.2016 · 25 citationsarXivon Valency
Unbiased Learning-to-Rank with Biased Feedback1608.04468v1 · Thorsten Joachims, Adith Swaminathan, Tobias Schnabel2016 · 528 citationsarXiv
Off-policy evaluation for slate recommendation1605.04812v3 · Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal et al.2016 · 58 citationsarXivon Valency
Unbiased Comparative Evaluation of Ranking Functions1604.07209v1 · Tobias Schnabel, Adith Swaminathan, Peter Frazier et al.2016 · 25 citationsarXiv
Recommendations as Treatments: Debiasing Learning and Evaluation1602.05352v2 · Tobias Schnabel, Adith Swaminathan, Ashudeep Singh et al.2016 · 268 citationsarXivon Valency
Counterfactual Risk Minimization: Learning from Logged Bandit Feedback1502.02362v2 · Adith Swaminathan, Thorsten Joachims2015 · 173 citationsarXivon Valency
Career total: 55 works. 30 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.