Publications (17)
HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation
Haoran Liu, Yuwei Zhang, Xiyao Li +2
Reinforcement learning typically improves multi-turn agent capabilities through the terminal outcome of the trajectories, which makes it difficult to determine credit assignments f…
SURGE: On the Potential of Large Language Models as General-Purpose Surrogate Code Executors
Bohan Lyu, Siqiao Huang, Zichen Liang
Neural surrogate models are powerful and efficient tools in data mining. Meanwhile, large language models (LLMs) have demonstrated remarkable capabilities in code-related tasks, su…
Adapting While Learning: Grounding LLMs for Scientific Problems with Intelligent Tool Usage Adaptation
Bohan Lyu, Yadi Cao, Duncan Watson-Parris +3
Large Language Models (LLMs) demonstrate promising capabilities in solving scientific problems but often suffer from the issue of hallucination. While integrating LLMs with tools c…
MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks
Jiacheng Chen, Tianhao Liang, Sherman Siu +13
We present MEGA-Bench, an evaluation suite that scales multimodal evaluation to over 500 real-world tasks, to address the highly heterogeneous daily use cases of end users. Our obj…
Analytical Calculation of Viscosity in Rouse Networks Below Gelation Transition
Bohan Lyu, Jie Lin
This work establishes an exact relationship between the zero-shear viscosity and the radius of gyration for generalized Rouse model with arbitrary network configurations. Building…
Convex-area-wise Linear Regression and Algorithms for Data Analysis
Bohan Lyu, Jianzhong Li
This paper introduces a new type of regression methodology named as Convex-Area-Wise Linear Regression(CALR), which separates given datasets by disjoint convex areas and fits diffe…
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…
Agents' Last Exam
Yiyou Sun, Xinyang Han, Weichen Zhang +306
Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional d…
An Efficient Data Analysis Method for Big Data using Multiple-Model Linear Regression
Bohan Lyu, Jianzhong Li
This paper introduces a new data analysis method for big data using a newly defined regression model named multiple model linear regression(MMLR), which separates input datasets in…
Exploring Diffusion Models' Corruption Stage in Few-Shot Fine-tuning and Mitigating with Bayesian Neural Networks
Xiaoyu Wu, Jiaru Zhang, Yang Hua +4
Few-shot fine-tuning of Diffusion Models (DMs) is a key advancement, significantly reducing training costs and enabling personalized AI applications. However, we explore the traini…
VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation
Xuan He, Dongfu Jiang, Ge Zhang +16
The recent years have witnessed great advances in video generation. However, the development of automatic video metrics is lagging significantly behind. None of the existing metric…
Scalable Behaviour Cloning on Browser Using via Skill Distillation
Kaisen Yang, Zheng Jiang, Yuzhao Peng +11
Internet users collectively perform an enormous range of skilled work through web browsers, from software development and document editing to search, forms, and enterprise workflow…
Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub
Bohan Lyu, Xin Cong, Heyang Yu +9
Large Language Models (LLMs) excel in traditional natural language processing tasks but struggle with problems that require complex domain-specific calculations or simulations. Whi…
Self-organized criticality driven by droplet influx and random fusion
Bohan Lyu, Jie Lin
The droplet size distribution typically decays exponentially in solutions formed by liquid-liquid phase separation. Nevertheless, a power-law distribution of nucleoli volumes has b…
Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving
Yong Lin, Shange Tang, Bohan Lyu +8
We introduce Goedel-Prover, an open-source language model that achieves state-of-the-art (as of April 5 2025) performance in automated formal proof generation for mathematical prob…
Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction
Yong Lin, Shange Tang, Bohan Lyu +17
We introduce Goedel-Prover-V2, a series of open-source language models that set a new state-of-the-art in automated theorem proving. Built on the standard expert iteration and rein…
Ineq-Comp: Benchmarking Human-Intuitive Compositional Reasoning in Automated Theorem Proving on Inequalities
Haoyu Zhao, Yihan Geng, Shange Tang +5
LLM-based formal proof assistants (e.g., in Lean) hold great promise for automating mathematical discovery. But beyond syntactic correctness, do these systems truly understand math…