collaborators

6 papers

cs.CR2026

CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity Capabilities

Tianneng Shi, Robin Rheem, Dongwei Jiang +13

AI has the potential to transform cybersecurity by enabling systems that can autonomously detect, analyze, and remediate software vulnerabilities. However, existing cybersecurity e…

cs.LG2026

Supplement Generation Training for Enhancing Agentic Task Performance

Young Min Cho, Daniele Bonadiman, Divya Bhargavi +8

Training large foundation models for agentic tasks is increasingly impractical due to the high computational costs, long iteration cycles, and rapid obsolescence as new models are…

cs.CL2025

Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback

Dongwei Jiang, Alvin Zhang, Andrew Wang +2

Recent studies have shown LLMs possess some ability to improve their responses when given external feedback. However, it remains unclear how effectively and thoroughly these models…

cs.AI2025

RATIONALYST: Mining Implicit Rationales for Process Supervision of Reasoning

Dongwei Jiang, Guoxuan Wang, Yining Lu +5

The reasoning steps generated by LLMs might be incomplete, as they mimic logical leaps common in everyday communication found in their pre-training data: underlying rationales are…

cs.CL2025

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

Zayne Sprague, Fangcong Yin, Juan Diego Rodriguez +7

Chain-of-thought (CoT) via prompting is the de facto method for eliciting reasoning capabilities from large language models (LLMs). But for what kinds of tasks is this extra ``thin…

cs.CL2025

Benchmarking Language Model Creativity: A Case Study on Code Generation

Yining Lu, Dixuan Wang, Tianjian Li +4

As LLMs become increasingly prevalent, it is interesting to consider how ``creative'' these models can be. From cognitive science, creativity consists of at least two key character…