activity
20242026
collaborators

11 papers

cs.CL2026

DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data

Zhen Huang, Yikun Wang, Shijie Xia +1

Pretraining data processing is critical to the downstream performance of Large Language Models (LLMs). However, many existing approaches define a fixed processing strategy at the c…

cs.IR2026

Diagnosing and Mitigating Context Rot in Long-horizon Search

Shijie Xia, Yikun Wang, Zhen Huang +1

Extensive context has become the norm as Large Language Models (LLMs) are increasingly deployed in long-horizon search tasks. The concern that increasing context length degrades mo…

cs.AI2026

AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts

Keyu Li, Junhao Shi, Yang Xiao +11

Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain f…

cs.AI2026

SR-Scientist: Scientific Equation Discovery With Agentic AI

Shijie Xia, Yuhan Sun, Pengfei Liu

Recently, Large Language Models (LLMs) have been applied to scientific equation discovery, leveraging their embedded scientific knowledge for hypothesis generation. However, curren…

cs.AI2025

Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Training

Dayuan Fu, Yunze Wu, Xiaojie Cai +13

Large Language Model (LLM) agents have recently shown strong potential in domains such as automated coding, deep research, and graphical user interface manipulation. However, train…

cs.AI2025

InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research

Yunze Wu, Dayuan Fu, Weiye Si +13

AI agents could accelerate scientific discovery by automating hypothesis formation, experiment design, coding, execution, and analysis, yet existing benchmarks probe narrow skills…