RT
Rajeev Thakur
cs.DCcs.AIcs.LGcs.CLcs.MAcs.PFcond-mat.mtrl-scics.ARcs.CEcs.GT
On Valency
published · living versionsW_p5cpt2cd·v1 · currentpublished
Beyond Division of Labor: How Roles Shape Feedback and Recovery in Multi-Agent Systems
with Chih-Hsuan Yang, Xinyang Li, Feng Yan
1 version
W_e69xqucw·v1published
Preprints & journals
23 papers in the corpus · 2021–2026LAM: Efficient Lossy Agent Memory Framework With A Retrieval-Score Error Bound2609.32256v1 · Baixi Sun, Le Chen, Anjir Ahmed Chowdhury et al.2026 · 0 citationsarXiv
Measure Before You Manage: Evaluating Agent Working Memory in Coding Agents2608.31057v1 · Le Chen, Zishen Wan, Baixi Sun et al.2026 · 0 citationsarXiv
FABRICA: Agentic CUDA-to-CSL Translation and Optimization for Wafer-Scale Systems2608.25124v1 · Yuebo Luo, Eliu Huerta, Venkatram Vishwanath et al.2026 · 0 citationsarXiv
What Confidence Routing Is Actually Doing: Auditing Routing, Calibration, and Commitment in Multi-Agent Deliberation2609.27822v1 · Jingyan Jiang, Huihuo Zheng, Rajeev Thakur et al.2026 · 0 citationsarXiv
LLMs Can Predict Failure Risk, But Struggle to Predict Which Collaboration Protocol Pays Off: Cost-Aware Protocol Routing Across Reasoning Tasks2608.14927v1 · Chih-Hsuan Yang, Jingyan Jiang, Cheng-Hau Yang et al.2026 · 0 citationsarXiv
Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning2607.15388v1 · Chih-Hsuan Yang, Jingyan Jiang, Vikram Vasudevan et al.2026 · 0 citationsarXiv
Implementing True MPI Sessions and Evaluating MPI Initialization Scalability2605.03983v1 · Hui Zhou, Kenneth Raffenetti, Yanfei Guo et al.2026 · 1 citationarXiv
Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents2511.10687v3 · Chih-Hsuan (Bella) Yang, Tanwi Mallick, Le Chen et al.2025 · 0 citationsarXiv
FIRST: Federated Inference Resource Scheduling Toolkit for Scientific AI Model Access2510.13724v1 · Aditya Tanikanti, Benoit Cot'e, Yanfei Guo et al.2025 · 5 citationsSC Workshops '25, Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, ACM, pp. 52-60, 2025
Evaluating the Safety and Skill Reasoning of Large Reasoning Models Under Compute Constraints2509.18382v1 · Adarsha Balaji, Le Chen, Rajeev Thakur et al.2025 · 0 citationsarXiv
ZCCL: Significantly Improving Collective Communication With Error-Bounded Lossy Compression2502.18554v1 · Jiajun Huang, Sheng Di, Xiaodong Yu et al.2025 · 1 citationarXiv
Employing Artificial Intelligence to Steer Exascale Workflows with Colmena2408.14434v1 · Logan Ward, J. Gregory Pauloski, Valerie Hayot-Sasson et al.2024 · 7 citationsarXiv
MPI Progress For All2405.13807v2 · Hui Zhou, Robert Latham, Ken Raffenetti et al.2024 · 7 citationsarXiv
Designing and Prototyping Extensions to MPI in MPICH2402.12274v1 · Hui Zhou, Ken Raffenetti, Yanfei Guo et al.2024 · 1 citationarXiv
Frustrated with MPI+Threads? Try MPIxThreads!2401.16551v1 · Hui Zhou, Ken Raffenetti, Junchao Zhang et al.2024 · 5 citationsarXiv
A Comprehensive Performance Study of Large Language Models on Novel AI Accelerators2310.04607v1 · Murali Emani, Sam Foreman, Varuni Sastry et al.2023 · 5 citationsarXiv
gZCCL: Compression-Accelerated Collective Communication Framework for GPU Clusters2308.05199v2 · Jiajun Huang, Sheng Di, Xiaodong Yu et al.2023 · 24 citationsarXiv
Quantifying the Performance Benefits of Partitioned Communication in MPI2308.03930v2 · Thomas Gillis, Ken Raffenetti, Hui Zhou et al.2023 · 7 citationsarXiv
Accelerating MPI Collectives with Process-in-Process-based Multi-object Techniques2305.10612v1 · Jiajun Huang, Kaiming Ouyang, Yujia Zhai et al.2023 · 2 citationsarXiv
An Optimized Error-controlled MPI Collective Framework Integrated with Lossy Compression2304.03890v3 · Jiajun Huang, Sheng Di, Xiaodong Yu et al.2023 · 22 citationsarXiv
Cloud Services Enable Efficient AI-Guided Simulation Workflows across Heterogeneous Resources2303.08803v1 · Logan Ward, J. Gregory Pauloski, Valerie Hayot-Sasson et al.2023 · 14 citationsarXiv
MPIX Stream: An Explicit Solution to Hybrid MPI+X Programming2208.13707v2 · Hui Zhou, Ken Raffenetti, Yanfei Guo et al.2022 · 26 citationsarXiv
Colmena: Scalable Machine-Learning-Based Steering of Ensemble Simulations for High Performance Computing2110.02827v1 · Logan Ward, Ganesh Sivaraman, J. Gregory Pauloski et al.2021 · 52 citationsarXiv
Career total: 269 works. 23 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.