5 citations · 6 across the 13 of their papers we have counts for
13 papers
FrontierChallenge: Evaluating Scientific Workflow Completion
Liangcai Su, Zhaopeng Feng, Zhuo Chen +14
Scientific agents increasingly analyze data, execute code, and produce research artifacts, yet most benchmarks emphasize final answers, isolated programs, or a single domain. We in…
Apodex 1.1: Scaling Agentic Intelligence for Complex Work
B. An, B. Li, B. Wang +72
General-purpose language models can reason and synthesize knowledge, but complex work also requires sustained interaction with files, information sources, and executable code, toge…
Visored: A Controlled-Natural-Language Prover for LLM-Generated Mathematics
Xiyu Zhai, Xinyi Chen, Yiping Wang +3
We present a dependent-type-based prover designed around the way LLMs (and humans) tend to write mathematics, complementing existing systems such as Lean and Rocq. Its core design…
PBT-Bench: Benchmarking AI Agents on Property-Based Testing
Lucas Jing, Xinqi Wang, Liao Zhang +1
Existing code benchmarks measure whether an agent can produce any test that reproduces a known bug, or whether it can produce a patch that fixes a described issue. Neither isolates…
Argus: Evidence Assembly for Scalable Deep Research Agents
Zhen Zhang, Liangcai Su, Zhuo Chen +7
Deep research agents have achieved remarkable progress on complex information seeking tasks. Even long ReAct style rollouts explore only a single trajectory, while recent state of…
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
Bohan Lyu, Yucheng Yang, Siqiao Huang +25
Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonstrate advanced capabilities i…
Unregularized Linear Convergence in Zero-Sum Game from Preference Feedback
Shulun Chen, Runlong Zhou, Zihan Zhang +2
Aligning large language models (LLMs) with human preferences has proven effective for enhancing model capabilities, yet standard preference modeling using the Bradley-Terry model a…
Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO
Ruizhe Shi, Minhak Song, Runlong Zhou +3
We present a fine-grained theoretical analysis of the performance gap between two-stage reinforcement learning from human feedback~(RLHF) and direct preference optimization~(DPO).…
Transformers are Efficient Compilers, Provably
Xiyu Zhai, Runlong Zhou, Liao Zhang +1
Transformer-based large language models (LLMs) have demonstrated surprisingly robust performance across a wide range of language-related tasks, including programming language under…
The Crucial Role of Samplers in Online Direct Preference Optimization
Ruizhe Shi, Runlong Zhou, Simon S. Du
Direct Preference Optimization (DPO) has emerged as a stable, scalable, and efficient solution for language model alignment. Despite its empirical success, the optimization propert…
Rethinking Transformers in Solving POMDPs
Chenhao Lu, Ruizhe Shi, Yuyao Liu +3
Sequential decision-making algorithms such as reinforcement learning (RL) in real-world scenarios inevitably face environments with partial observability. This paper scrutinizes th…
Reflect-RL: Two-Player Online RL Fine-Tuning for LMs
Runlong Zhou, Simon S. Du, Beibin Li
As language models (LMs) demonstrate their capabilities in various fields, their application to tasks requiring multi-round interactions has become increasingly popular. These task…
Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning
Ruizhe Shi, Yuyao Liu, Yanjie Ze +2
Offline reinforcement learning (RL) aims to find a near-optimal policy using pre-collected datasets. In real-world scenarios, data collection could be costly and risky; therefore,…