SS
Swarnadeep Saha
cs.CLcs.AIcs.LGcs.LOcs.SE
On Valency
published · living versionsW_kwzn9zcn·v1 · currentpublished
Aligning Autoresearch: Co-Improvement between Agents and Humans
with Tianjian Li, Chuanyang Jin, Seungone Kim, Tong Chen +8
1 version
Preprints & journals
26 papers in the corpus · 2019–2026Autodata: An agentic data scientist to create high quality synthetic data2606.25996v3 · Ilia Kulikov, Chenxi Whitehouse, Tianhao Wu et al.2026 · 0 citationsarXiv
Reasoning over mathematical objects: on-policy reward modeling and test time aggregation2603.18886v1 · Pranjal Aggarwal, Marjan Ghazvininejad, Seungone Kim et al.2026 · 0 citationsarXiv
Text-to-Stage: Spatial Layouts from Long-form Narratives2603.17832v1 · Jefferson Hernandez, Swarnadeep Saha, Chenxi Whitehouse et al.2026 · 0 citationsarXiv
Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense2510.07242v3 · Leitian Tao, Ilia Kulikov, Swarnadeep Saha et al.2025 · 0 citationsarXiv
The Majority is not always right: RL training for solution aggregation2509.06870v1 · Wenting Zhao, Pranjal Aggarwal, Swarnadeep Saha et al.2025 · 0 citationsarXiv
Jointly Reinforcing Diversity and Quality in Language Model Generations2509.02534v1 · Tianjian Li, Yiming Zhang, Ping Yu et al.2025 · 2 citationsarXiv
OptimalThinkingBench: Evaluating Over and Underthinking in LLMs2508.13141v2 · Pranjal Aggarwal, Seungone Kim, Jack Lanchantin et al.2025 · 1 citationarXiv
Bridging Offline and Online Reinforcement Learning for LLMs2506.21495v1 · Jack Lanchantin, Angelica Chen, Janice Lan et al.2025 · 0 citationsarXiv
J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning2505.10320v3 · Chenxi Whitehouse, Tianlu Wang, Ping Yu et al.2025 · 1 citationarXiv
Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge2501.18099v2 · Swarnadeep Saha, Xian Li, Marjan Ghazvininejad et al.2025 · 0 citationsarXiv
MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning2409.12147v2 · Justin Chih-Yao Chen, Archiki Prasad, Swarnadeep Saha et al.2024 · 4 citationsarXiv
System-1.x: Learning to Balance Fast and Slow Planning with Language Models2407.14414v2 · Swarnadeep Saha, Archiki Prasad, Justin Chih-Yao Chen et al.2024 · 1 citationarXiv
MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models2402.01620v2 · Justin Chih-Yao Chen, Swarnadeep Saha, Elias Stengel-Eskin et al.2024 · 1 citationarXiv
Branch-Solve-Merge Improves Large Language Model Evaluation and Generation2310.15123v2 · Swarnadeep Saha, Omer Levy, Asli Celikyilmaz et al.2023 · 12 citationsarXiv
ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs2309.13007v3 · Justin Chih-Yao Chen, Swarnadeep Saha, Mohit Bansal2023 · 64 citationsarXiv
Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Personalization2306.09299v2 · Swarnadeep Saha, Peter Hase, Mohit Bansal2023 · 1 citationarXiv
ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness2304.10703v2 · Archiki Prasad, Swarnadeep Saha, Xiang Zhou et al.2023 · 12 citationsarXiv
MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation2212.08607v1 · Swarnadeep Saha, Xinyan Velocity Yu, Mohit Bansal et al.2022 · 8 citationsarXiv
Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations2211.07517v1 · Swarnadeep Saha, Peter Hase, Nazneen Rajani et al.2022 · 8 citationsarXiv
Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees2209.10492v2 · Swarnadeep Saha, Shiyue Zhang, Peter Hase et al.2022 · 8 citationsarXiv
Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning2204.04813v1 · Swarnadeep Saha, Prateek Yadav, Mohit Bansal2022 · 6 citationsarXiv
multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning2106.01354v1 · Swarnadeep Saha, Prateek Yadav, Mohit Bansal2021 · 18 citationsarXiv
ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning2104.07644v3 · Swarnadeep Saha, Prateek Yadav, Lisa Bauer et al.2021 · 31 citationsarXiv
ConjNLI: Natural Language Inference Over Conjunctive Sentences2010.10418v2 · Swarnadeep Saha, Yixin Nie, Mohit Bansal2020 · 24 citationsarXiv
PRover: Proof Generation for Interpretable Reasoning over Rules2010.02830v1 · Swarnadeep Saha, Sayan Ghosh, Shashank Srivastava et al.2020 · 50 citationsarXiv
Joint Multi-Domain Learning for Automatic Short Answer Grading1902.09183v1 · Swarnadeep Saha, Tejas I. Dhamecha, Smit Marvaniya et al.2019 · 6 citationsarXiv
Career total: 46 works. 26 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.