10 papers
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
Tong Zheng, Xidong Wu, Zheng Zhang +14
Recursive self-improvement is becoming essential for autonomous AI agents, whose progress depends on discovering high-value solutions across complex domains. Effective exploration…
Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization
Kaishen Wang, Tong Zheng, Xuehao Cui +3
Large reasoning models (LRMs) improve language model capabilities by generating explicit thinking traces before final answers. In factuality-oriented question answering (QA), such…
Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling
Runpeng Dai, Tong Zheng, Rui Liu +2
Test-time scaling improves the reasoning performance of large language models but incurs substantial cost in both total computation and latency. Existing adaptive sampling methods…
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
Tong Zheng, Haolin Liu, Chengsong Huang +10
Test-time scaling (TTS) has become an effective approach for improving large language model performance by allocating additional computation during inference. However, existing TTS…
G-Zero: Self-Play for Open-Ended Generation from Zero Data
Chengsong Huang, Haolin Liu, Tong Zheng +7
Self-evolving LLMs excel in verifiable domains but struggle in open-ended tasks, where reliance on proxy LLM judges introduces capability bottlenecks and reward hacking. To overcom…
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification
Rui Liu, Dian Yu, Zhenwen Liang +6
Aligning Multimodal Large Language Models (MLLMs) requires reliable reward models, yet existing single-step evaluators can suffer from lazy judging, exploiting language priors over…
Reinforcing Multimodal Reasoning Against Visual Degradation
Rui Liu, Dian Yu, Haolin Liu +6
Reinforcement Learning has significantly advanced the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet the resulting policies remain brittle against real-wor…
Learning from Self-Debate: Preparing Reasoning Models for Multi-Agent Debate
Chenxi Liu, Yanshuo Chen, Ruibo Chen +3
The reasoning abilities of large language models (LLMs) have been substantially improved by reinforcement learning with verifiable rewards (RLVR). At test time, collaborative reaso…
ImAgent: A Unified Multimodal Agent Framework for Test-Time Scalable Image Generation
Kaishen Wang, Ruibo Chen, Tong Zheng +1
Recent text-to-image (T2I) models have made remarkable progress in generating visually realistic and semantically coherent images. However, they still suffer from randomness and in…
Model Correlation Detection via Random Selection Probing
Ruibo Chen, Sheng Zhang, Yihan Wu +3
The growing prevalence of large language models (LLMs) and vision-language models (VLMs) has heightened the need for reliable techniques to determine whether a model has been fine-…