12 papers
CollabFlow: Recursive Self-Improvement of Agent Collaboration
Xiao Huang, Mingda Zhang, Junming Zhang +5
Recursive self-improvement (RSI) lets a system improve from its own outcomes; in LLM-based multi-agent systems, Agents refine one another within a task, and outcomes improve how th…
EvoSteer: Online Self-Evolving Graph Orchestration via Reference-Anchored Credit Assignment
Mingda Zhang, Hanwen Zhang, Qiang Huang +5
In recent years, LLM-based multi-agent systems have been widely applied to orchestrate tool-using agents into executable communication graphs. However, existing self-evolving orche…
R Flow: Recursive Self-Improvement via Recursive Skill Evolution
Mingda Zhang, Qiang Huang, Yanjin Li +4
LLM-based agents can improve themselves across tasks by reusing and revising the skills they orchestrate into executable procedures. Flow-based training fits this loop: it samples…
Beyond Prompt or Skill? Attribution-Guided Optimization of Modular LLM Programs
Haoran Shou, Haoyue Liu, Yu Huo +2
Large language models can solve increasingly diverse reasoning tasks, yet their performance remains highly sensitive to task prompts, intermediate instructions, and the way reusabl…
SIGMA: Skill-Incidence Graphs for Compositional Multi-Agent Design
Kun Zeng, Yu Huo, Siyu Zhang +5
Existing graph-based multi-agent system (MAS) designers mainly improve collaboration by optimizing communication topologies over predefined agents, roles, or groups. However, becau…
Voices Across Registers: Corpus-Conditioned Vernacular Jailbreaks against Aligned LLMs via Fanfiction Subgenres
Zhongze Luo, Ruihe Shi, Zhenshuai Yin +3
Existing jailbreaks against aligned LLMs are discrete artifacts whose surface forms are easy to fingerprint and patch. We argue that the broader failure mode may lie not in any spe…
SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration
Mingda Zhang, Tiesunlong Shen, Haoran Luo +4
In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex tasks through task orchestration. However, existing orchestration methods sti…
Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries
Kun Zeng, Yu Huo, Siyu Zhang +6
Skill-augmented agents increasingly rely on large reusable skill libraries, but retrieving relevant skills is not the same as presenting usable context. Existing methods typically…
FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing
Mingda Zhang, Wenjin Liu, Tiesunlong Shen +5
In recent years, agentic workflows have been widely applied to solve complex human tasks. However, existing workflow construction still faces key challenges, including human-depend…
Shape of Thought: Progressive Object Assembly via Visual Chain-of-Thought
Yu Huo, Siyu Zhang, Kun Zeng +7
Multimodal models for text-to-image generation have achieved strong visual fidelity, yet they remain brittle under compositional structural constraints, notably generative numeracy…
RepoShapley: Shapley-Enhanced Context Filtering for Repository-Level Code Completion
Yu Huo, Kun Zeng, Siyu Zhang +4
Repository-level code completion benefits from retrieval-augmented generation (RAG). However, controlling cross-file evidence is difficult because chunk utility is often interactio…
Optimal Boost Design for Auto-bidding Mechanism with Publisher Quality Constraints
Huanyu Yan, Yu Huo, Min Lu +4
Online bidding serves as a fundamental information system in mobile ecosystems, facilitating real-time ad allocation across billions of devices while optimizing both platform perfo…