Zhengwen Zeng

Yang Wan, Zheng Cao, Zhenhao Zhang et al.

Large language models excel as few-shot learners when provided with appropriate demonstrations, yet this strength becomes problematic in multiturn agent scenarios, where LLMs erroneously mimic their own previous responses as few-shot examples. Through attention analysis, we identify conversational inertia, a phenomenon where models exhibit strong diagonal attention to previous responses, which is associated with imitation bias that constrains exploration. This reveals a tension when transforming few-shot LLMs into agents: longer context enriches environmental feedback for exploitation, yet also amplifies conversational inertia that undermines exploration. Our key insight is that for identical states, actions generated with longer contexts exhibit stronger inertia than those with shorter contexts, enabling construction of preference pairs without environment rewards. Based on this, we propose Context Preference Learning to calibrate model preferences to favor low-inertia responses over highinertia ones. We further provide context management strategies at inference time to balance exploration and exploitation. Experimental results across eight agentic environments and one deep research scenario validate that our framework reduces conversational inertia and achieves performance improvements.

Xinyu Qiu, Heng Jia, Zhengwen Zeng et al.

Parallel test-time scaling typically trains separate generation and verification models, incurring high training and inference costs. We propose Advantage Decoupled Preference Optimization (ADPO), a unified reinforcement learning framework that jointly learns answer generation and self-verification within a single policy. ADPO introduces two innovations: a preference verification reward improving verification capability and a decoupled optimization mechanism enabling synergistic optimization of generation and verification. Specifically, the preference verification reward computes mean verification scores from positive and negative samples as decision thresholds, providing positive feedback when prediction correctness aligns with answer correctness. Meanwhile, the advantage decoupled optimization computes separate advantages for generation and verification, applies token masks to isolate gradients, and combines masked GRPO objectives, preserving generation quality while calibrating verification scores. ADPO achieves up to +34.1% higher verification AUC and -53.5% lower inference time, with significant gains of +2.8%/+1.4% accuracy on MathVista/MMMU, +1.9 cIoU on ReasonSeg, and +1.7%/+1.0% step success rate on AndroidControl/GUI Odyssey.