Anurag Beniwal

Researcher, Elevenlabs

Joined

October 2022

Names

Anurag Beniwal (Preferred)

Emails

****@umich.edu (Confirmed)

****@gmail.com (Confirmed)

****@elevenlabs.io (Confirmed)

Personal Links

Google Scholar

Career & Education History

Researcher

Elevenlabs (elevenlabs.io)

2025 – Present

Researcher

Amazon (amazon.com)

2017 – 2025

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training
Chenlu Ye, Zhou Yu, Ziji Zhang, Hao Chen, Narayanan Sadagopan, Jing Huang, Tong Zhang, Anurag Beniwal
- MATH-AI 2025 Poster
- Readers: Everyone
Rethinking Alignment in Cross-Lingual Knowledge Transfer
Xueying Bai, Yingying Zhuang, Zhou Yu, Jing Huang, Ziji Zhang, Aman Gupta, Anurag Beniwal
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
TRIM: Hybrid Inference via Targeted Stepwise Routing in Multi-Step Reasoning Tasks
Vansh Kapoor, Aman Gupta, Hao Chen, Anurag Beniwal, Jing Huang, Aviral Kumar
- ICLR 2026 Poster
- Readers: Everyone
Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training
Chenlu Ye, Zhou Yu, Ziji Zhang, Hao Chen, Narayanan Sadagopan, Jing Huang, Tong Zhang, Anurag Beniwal
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
TOD-ProcBench: Benchmarking Complex Instruction-Following in Task-Oriented Dialogues
Sarik Ghazarian, Abhinav Gullapalli, Swair Shah, Anurag Beniwal, Nanyun Peng, Narayanan Sadagopan, Zhou Yu
- MTI-LLM @ NeurIPS 2025 Poster
- Readers: Everyone
Semantic Volume: Quantifying and Detecting both External and Internal Uncertainty in LLMs
Xiaomin Li, Zhou Yu, Ziji Zhang, Yingying Zhuang, Swair Shah, Narayanan Sadagopan, Anurag Beniwal
- SPIGM @ NeurIPS
- Readers: Everyone
How and Where to Translate? The Impact of Translation Strategies in Cross-lingual LLM Prompting
Aman Gupta, Yingying Zhuang, Anurag Beniwal
- KDD 2025 Workshop on Prompt Optimization Poster
- Readers: Everyone
When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs
Xiaomin Li, Zhou Yu, Zhiwei Zhang, Xupeng Chen, Ziji Zhang, Yingying Zhuang, Narayanan Sadagopan, Anurag Beniwal
- NeurIPS 2025 spotlight
- Readers: Everyone
DARD: A Multi-Agent Approach for Task-Oriented Dialog Systems
Aman Gupta, Anirudh Ravichandran, Ziji Zhang, Swair Shah, Anurag Beniwal, Narayanan Sadagopan
- NeurIPS 2024 Workshop Open-World Agents Poster
- Readers: Everyone
MERLIN: Multiple Enhanced Representations with LLM Generated INdices
Anirudh Ravichandran, Yidong Zou, Jayaprakash Baskar, Anurag Beniwal
- Gen-IR_SIGIR24
- Readers: Everyone

View all 11 publications