Hamed Zamani
3 papers · Latest:
Artificial Intelligence
COSEARCH: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search
CoSearch proposes a reinforcement learning framework that jointly trains reasoning agents and document rankers for agentic search, overcoming retrieval bottlenecks.
2604.17555
Information RetrievalA Unified Model and Document Representation for On-Device Retrieval-Augmented Generation
A unified model for on-device RAG compresses context and uses shared representations, drastically reducing memory and disk usage while matching performance.
2604.14403
Information RetrievalEvaluation of Agents under Simulated AI Marketplace Dynamics
This paper introduces Marketplace Evaluation, a simulation-based paradigm to assess AI systems in competitive marketplace dynamics, moving beyond static benchmarks.
2604.14256
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.