collaborators

7 papers

cs.CL2026

Tmax: A simple recipe for terminal agents

Hamish Ivison, Junjie Oscar Yin, Rulin Shao +3

Terminal-using agents have quickly become the most popular downstream application of language models (LMs). Despite their prevalence, relatively little academic work has examined R…

cs.CL2026

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

Zhepei Wei, Xiao Yang, Kai Sun +12

While large language models (LLMs) have demonstrated strong performance on factoid question answering, they are still prone to hallucination and untruthful responses, particularly…

cs.AI2026

JobBench: Aligning Agent Work With Human Will

Yuetai Li, Yichen Feng, Zhangchen Xu +21

Current benchmarks for occupational AI agents are scoped primarily by economic values, telling a replacement story. We introduce JobBench, which evaluates AI agents on the workflow…

cs.CL2026

DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

Rulin Shao, Akari Asai, Shannon Zejiang Shen +18

Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are trained on easily verifiable short-form…

cs.AI2026

EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics

Shuyue Stella Li, Rui Xin, Teng Xiao +8

Language models encode substantial evaluative knowledge from pretraining, yet current post-training methods rely on external supervision (human annotations, proprietary models, or…

cs.CL2025

SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning

Shicheng Liu, Kai Sun, Lisheng Fu +8

Semi-structured content in HTML tables, lists, and infoboxes accounts for a substantial share of factual data on the web, yet the formatting complicates usage, and reliably extract…