Jimmy Lin

Deep search agents that combine large language models with retrieval tools excel at complex, multi-hop queries. Yet, existing benchmarks such as BrowseComp rely on black-box web search APIs, facing key limitations. (1) Fairness: for agents, dynamic and opaque web APIs hinder reproducibility and f...

We present rosaOS, an open-source agentic operating system for embodied LLMs: interactive, LLM-driven agents coordinate various software tools and physical devices through a desktop companion, the Reachy Mini robot. Existing LLM–robotic systems are generally built as a tight, intertwined stack, m...

Deep research agents rely on iterative retrieval and reasoning to answer complex queries, but scaling test-time computation raises significant efficiency concerns. We study how to allocate reasoning budget in deep search pipelines, focusing on the role of listwise reranking. Using the BrowseComp-...

Retrieval benchmarks for large language models (LLMs) should reflect the long, reasoning-intensive queries typical of retrieval-augmented generation (RAG). We present a systematic study of BRIGHT, a reasoning-focused retrieval benchmark, along with strong, reproducible reference methods integrate...

Traditional short keyword queries are increasingly being replaced by longer, more detailed queries that reflect complex and nuanced user information needs, especially in conversational assistants equipped with web search capabilities. In this work, we present a methodology for automatically gener...

Recent approaches that leverage large language models (LLMs) for pseudo-relevance feedback (PRF) have generally not utilized well-established feedback models like Rocchio and RM3 when expanding queries for BM25. Instead, they often opt for a simple string concatenation of the query and LLM-genera...

We introduce Rank-R1, an LLM-based reranker that reasons over queries and candidate documents before ranking. Existing rerankers based on LLMs rely on prompting or fine-tuning to order documents by relevance without explicit reasoning. Rank-R1 uses reinforcement learning with only relevance label...

How do large language models (LLMs) know what they know? Answering this question has been difficult because pre-training data is often a ''black box'' – unknown or inaccessible. The recent release of nanochat – a family of small LLMs with fully open pre-training data – addresses this as it provid...

Large language models (LLMs) increasingly rely on retrieval-augmented generation (RAG), where search results are provided as external context to improve grounding and factuality. The Model Context Protocol (MCP) is an emerging industry standard for connecting LLMs to external tools. We present MC...

While dense retrieval models have been the standard for state-of-the-art information retrieval, their deployment is often constrained by high memory requirements and reliance on GPU accelerators for vector similarity search at scale. Learned sparse retrieval offers a compelling alternative by ena...