13 papers
RPO: Decoupling Rollout and Inference Policies for LLM Reasoning
Jingchu Wang, Bingbing Xu, Yige Yuan +4
Existing reinforcement learning methods for LLM reasoning implicitly assume that the policy generating training trajectories should coincide with the one producing inference respon…
GIFT: Games as Informal Training for Generalizable LLMs
Nuoyan Lyu, Bingbing Xu, Xueyun Tian +6
Recent LLMs excel at formal tasks such as mathematical reasoning and code generation, but still struggle with broader abilities such as planning, creativity, and social intelligenc…
Inference-time Alignment in Continuous Space
Yige Yuan, Teng Xiao, Li Yunfan +5
Aligning large language models with human feedback at inference time has received increasing attention due to its flexibility. Existing methods rely on generating multiple response…
Incentivizing Strong Reasoning from Weak Supervision
Yige Yuan, Teng Xiao, Shuchang Tao +4
Large language models (LLMs) have demonstrated impressive performance on reasoning-intensive tasks, but enhancing their reasoning abilities typically relies on either reinforcement…
Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems
Zixu Wang, Bingbing Xu, Yige Yuan +2
Multi-Agent Systems (MAS) built on large language models typically solve complex tasks by coordinating multiple agents through workflows. Existing approaches generates workflows ei…
Multi-Personality Generation of LLMs at Decoding-time
Rongxin Chen, Yunfan Li, Yige Yuan +2
Multi-personality generation for LLMs, enabling simultaneous embodiment of multiple personalization attributes, is a fundamental challenge. Existing retraining-based approaches are…