2 citations · 2 across the 13 of their papers we have counts for
14 papers
An Empirical Study of Harness Design for Coding Agents
Run-Ze Fan, Zihao Zhang, Simin Ma +6
Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering performance, yet existing work typically evaluates harnesses…
Safety-Regulated Transfer Reinforcement Learning with Adaptive Teacher Guidance
Wenjie Huang, Yang Li, Jingjia Teng +5
We propose Safety-Regulated Adaptive Transfer Reinforcement Learning (SRATRL), a teacher--student framework that combines safety-triggered intervention, safety-adaptive value shapi…
Understanding Knowledge Distillation in Post-Training: When It Helps and When It Fails
Xin Liu, Simin Ma, Shujian Liu +5
Large language models (LLMs) achieve strong performance across many tasks, but their high computational cost limits deployment in resource-constrained environments. Knowledge Disti…
CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use
Zhen Zhang, Kaiqiang Song, Xun Wang +11
AI agents are increasingly used to solve real-world tasks by reasoning over multi-turn user interactions and invoking external tools. However, applying reinforcement learning to su…
VC4VG: Optimizing Video Captions for Text-to-Video Generation
Yang Du, Zhuoran Lin, Kaiqiang Song +5
Recent advances in text-to-video (T2V) generation highlight the critical role of high-quality video-text pairs in training models capable of producing coherent and instruction-alig…
Communication to Completion: Modeling Collaborative Workflows with Intelligent Multi-Agent Communication
Yiming Lu, Xun Wang, Simin Ma +6
Multi-agent LLM systems have demonstrated impressive capabilities in complex collaborative tasks, yet most frameworks treat communication as instantaneous and free, overlooking a f…
Aligning Multilingual Reasoning with Verifiable Semantics from a High-Resource Expert Model
Fahim Faisal, Kaiqiang Song, Song Wang +4
While reinforcement learning has advanced the reasoning abilities of Large Language Models (LLMs), these gains are largely confined to English, creating a significant performance d…
TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning
Simin Ma, Shujian Liu, Jun Tan +7
Diverse instruction data is vital for effective instruction tuning of large language models, as it enables the model to generalize across different types of inputs . Building such…
LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries
Ming Yin, Dinghan Shen, Silei Xu +11
Tool calling has emerged as a critical capability for AI agents. In contrast to conventional tool calling frameworks that rely on static, provider-specific tool definitions, the Mo…
LogicIF: Towards Complex Logic Instruction Following
Mian Zhang, Shujian Liu, Sixun Dong +9
Instruction following has catalyzed the recent era of Large Language Models (LLMs) and is the foundational skill underpinning more advanced capabilities such as reasoning and agent…
Composing Policy Gradients and Prompt Optimization for Language Model Programs
Noah Ziems, Dilara Soylu, Lakshya A Agrawal +10
Group Relative Policy Optimization (GRPO) has proven to be an effective tool for post-training language models (LMs). However, AI systems are increasingly expressed as modular prog…
Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
Tong Wu, Shujian Zhang, Kaiqiang Song +7
Large Language Models (LLMs) are susceptible to security and safety threats, such as prompt injection, prompt extraction, and harmful requests. One major cause of these vulnerabili…
Improving Multilingual Instruction Finetuning via Linguistically Natural and Diverse Datasets
Sathish Reddy Indurthi, Wenxuan Zhou, Shamil Chollampatt +4
Advancements in Large Language Models (LLMs) have significantly enhanced instruction-following capabilities. However, most Instruction Fine-Tuning (IFT) datasets are predominantly…
WPO: Enhancing RLHF with Weighted Preference Optimization
Wenxuan Zhou, Ravi Agrawal, Shujian Zhang +5
Reinforcement learning from human feedback (RLHF) is a promising solution to align large language models (LLMs) more closely with human values. Off-policy preference optimization,…