11 papers
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…
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…
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…
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…
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…
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…