activity
20242026
collaborators

10 papers

cs.AI2026

Beyond Confidence: Test-Time Scaling for Multi-Turn Search Agents via Retrieval Grounding

Hyunho Kook, Junhyuk So, Tianyu Fu +2

Confidence-based voting aggregates parallel LLM rollouts by weighting each with internal signals such as token log probabilities, and has been actively studied for single-turn reas…

cs.CL2026

Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models

Tianyu Fu, Yichen You, Zekai Chen +3

Improving the reasoning abilities of Large Language Models (LLMs), especially under parameter constraints, is crucial for real-world applications. Looped transformers address this…

cs.AI2026

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

Xinlei Yu, Zhangquan Chen, Yongbo He +36

Latent space is rapidly emerging as a native substrate for language-based models. While modern systems are still commonly understood through explicit token-level generation, an inc…

cs.CL2026

Cache-to-Cache: Direct Semantic Communication Between Large Language Models

Tianyu Fu, Zihan Min, Hanling Zhang +4

Multi-LLM systems harness the complementary strengths of diverse Large Language Models, achieving performance and efficiency gains that are not attainable by a single model. In exi…

cs.AI2025

Reducing Latency of LLM Search Agent via Speculation-based Algorithm-System Co-Design

Zixiao Huang, Wen Zeng, Tianyu Fu +10

LLM-based search agents achieve strong performance but suffer from severe latency, as each step requires serialized LLM reasoning followed by action of tool execution. We revisit t…

cs.LG2025

Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths

Tianyu Fu, Haofeng Huang, Xuefei Ning +10

Sliding-window attention offers a hardware-efficient solution to the memory and throughput challenges of Large Language Models (LLMs) in long-context scenarios. Existing methods ty…