9 papers
Questioning the Questions: Sustaining Self-Evolution in Reasoning Models
Jinyuan Li, Chengsong Huang, Langlin Huang +4
Self-evolving reasoning models learn from their own generated questions, yet repeated self-training can lead to performance collapse. In this paper, we investigate why performance…
Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems
Shaoyang Xu, Jingshen Zhang, Long P. Hoang +2
Multicultural multi-agent systems are increasingly deployed in globally diverse settings, where different agents are grounded in different cultural backgrounds. Existing cultural e…
Process Rewards with Learned Reliability
Jinyuan Li, Langlin Huang, Chengsong Huang +5
Process Reward Models (PRMs) provide step-level feedback for reasoning, but current PRMs usually output only a single reward score for each step. Downstream methods must therefore…
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…
Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration
Langlin Huang, Chengsong Huang, Jinyuan Li +3
Reinforcement learning with verifiable rewards, particularly Group Relative Policy Optimization (GRPO), has significantly advanced the reasoning capabilities of Large Language Mode…
Training Data Efficiency in Multimodal Process Reward Models
Jinyuan Li, Chengsong Huang, Langlin Huang +4
Multimodal Process Reward Models (MPRMs) are central to step-level supervision for visual reasoning in MLLMs. Training MPRMs typically requires large-scale Monte Carlo (MC)-annotat…
Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent Evolution
Hongze Mi, Yibo Feng, WenJie Lu +11
Multimodal Large Language Model (MLLM) agents facilitate Graphical User Interface (GUI) automation but struggle with long-horizon, cross-application tasks due to limited context wi…
RelayLLM: Efficient Reasoning via Collaborative Decoding
Chengsong Huang, Tong Zheng, Langlin Huang +3
Large Language Models (LLMs) for complex reasoning is often hindered by high computational costs and latency, while resource-efficient Small Language Models (SLMs) typically lack t…
AutoPBO: LLM-powered Optimization for Local Search PBO Solvers
Jinyuan Li, Yi Chu, Yiwen Sun +2
Pseudo-Boolean Optimization (PBO) provides a powerful framework for modeling combinatorial problems through pseudo-Boolean (PB) constraints. Local search solvers have shown excelle…