12 papers
FDE-Bench: Evaluating End-to-End Delivery from Underspecified Real-World Business Requests
Huaiming Li, Can Huang, Chufan Wu +18
Real-world business requests often leave key requirements unstated because frontline practitioners struggle to articulate rules they know from experience. Forward-deployed engineer…
RLDISCOVER: LLM-driven co-evolution of reinforcement learning algorithms
Haoran Li, Zengle Ge, Xiaomin Yuan +14
LLM-guided program evolution has enabled discoveries in mathematics and computational optimization, raising the prospect of reinforcement learning (RL) algorithms that self-evolve…
AGAR: a reinforcement learning substrate for LLM program evolution
Haoran Li, Zengle Ge, Xiaomin Yuan +11
Given a task and an evaluator, a language model can rewrite a candidate program while a search loop decides which rewrites survive, offering a practical route to algorithm discover…
From Transient Prompts to Persistent Control: Scientific Poster Generation via Recursive Semantic-Geometric Contracts
Runze Li, Yukun Zhao, Can Xu +5
Scientific poster generation distills a multimodal paper into a single-page visual artifact, forcing strict trade-offs between informational coverage and readability under a fixed…
Navigating Sparse Evidence: Agentic Visual RAG via Explicit Context Selection and Consolidation
Yucheng Shen, Lingyong Yan, Jiulong Wu +4
Visual Retrieval-Augmented Generation (VRAG) empowers models to navigate and answer queries about visually rich documents by retrieving relevant page images as visual evidence and…
Janus: An Algorithm-Evaluator Co-Evolution Framework for LLM-Driven Discovery under Expensive Evaluation Budgets
Ximeng Liu, Qianlong Wang, Yingming Mao +6
LLM-driven program discovery relies on rapid evaluator feedback, but many scientific and engineering tasks require high-fidelity simulations, hardware execution, or physical experi…
Beyond Static Evaluation: Co-Evolutionary Mechanisms for LLM-Driven Strategy Evolution in Adversarial Games
Haoran Li, Zengle Ge, Ziyang Zhang +10
Recent advances in LLM-driven code evolution have enabled automated discovery by iteratively generating and improving programs. However, applying these methods to adversarial multi…
Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime
Tianshu Zhu, Wenyu Zhang, Xiaoying Zuo +8
Agentic reinforcement learning (RL) for software engineering spends much of its compute on stateful trajectories whose grouped binary rewards are highly skewed and weakly contrasti…
VISOR: Agentic Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning
Yucheng Shen, Jiulong Wu, Jizhou Huang +3
Visual Retrieval-Augmented Generation (VRAG) empowers Vision-Language Models to retrieve and reason over visually rich documents. To tackle complex queries requiring multi-step rea…
Qianfan-OCR: A Unified End-to-End Model for Document Intelligence
Daxiang Dong, Mingming Zheng, Dong Xu +17
We present Qianfan-OCR, a 4B-parameter end-to-end vision-language model that unifies document parsing, layout analysis, and document understanding within a single architecture. It…
QianfanHuijin Technical Report: A Novel Multi-Stage Training Paradigm for Finance Industrial LLMs
Shupeng Li, Weipeng Lu, Linyun Liu +16
Domain-specific enhancement of Large Language Models (LLMs) within the financial context has long been a focal point of industrial application. While previous models such as Bloomb…
The FM Agent
Annan Li, Chufan Wu, Zengle Ge +19
Large language models (LLMs) are catalyzing the development of autonomous AI research agents for scientific and engineering discovery. We present FM Agent, a novel and general-purp…