papers

Publications (17)

cs.AI2026

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…

cs.LG2026

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…

cs.LG2025

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…

cs.CV2025

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…

cond-mat.soft2025

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…

cs.DB2024

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…

cs.LG2026

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…

cs.AI2026

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…

cs.LG2023

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…

cs.CV2026

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…

cs.CV2024

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…

cs.CL2026

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…

cs.SE2025

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…

cond-mat.soft2025

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…

cs.LG2025

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…

cs.LG2025

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…

cs.AI2025

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…