12 papers · 1 filter
Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World
Kaixiang Yao, Xu Wang, Miao Pan +10
Spatial reasoning is essential for vision-language models (VLMs) to understand and act in the physical world. Reasoning in dynamic environments requires VLMs to perceive local stat…
Dual-Axis Policy Optimization for LLM Agents: Bayesian Feedback Attribution and Trajectory Mass Normalization
Yingxuan Zhuang, Binhe Yu, Jingxiao Yang +6
Reinforcement learning for LLM agents involves two distinct optimization di- mensions: how environment feedback is exploited within a trajectory, and how complete trajectories are…
Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization
Jingxiao Yang, Wangjie Gan, Yingxuan Zhuang +3
Outcome-based reinforcement learning provides verified feedback for language-model agents, but assigns trajectory-level advantage uniformly to all decisions, yielding coarse credit…
AttriMem: Attribution-Guided Process Feedback for Agent Memory Construction
Qinfeng Li, Yuntai Bao, Xinyan Yu +7
Effective memory is crucial for LLM agents, yet constructing it effectively remains challenging. A memory-construction policy decides what information to extract, store, update, co…
Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding
Yingxuan Zhuang, Jingxiao Yang, Miao Pan +7
MLLMs frequently hallucinate objects inconsistent with visual inputs. This issue is typically attributed to the over-reliance on language priors, which can override the visual cont…
VITAL: Visual-Semantic Dual Supervision for Enhanced and Interpretable Latent Reasoning in Medical MLLMs
Qiaoru Li, Shaotian Liang, Jintao Chen +4
Latent reasoning enables reasoning over continuous hidden states rather than explicit tokens, avoiding the language bottleneck and inference overhead of chain-of-thought for medica…
PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
Qinfeng Li, Yuntai Bao, Jianghui Hu +5
LLM agents rely on prompts to implement task-specific capabilities based on foundation LLMs, making agent prompts valuable intellectual property. However, in untrusted deployments,…
GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification
Wangjie Gan, Miao Pan, Linbo Xi +4
Large language models are typically post-trained using supervised fine-tuning (SFT) and reinforcement learning (RL), yet effectively unifying efficient knowledge injection with rob…
AST: Adaptive, Seamless, and Training-Free Precise Speech Editing
Sihan Lv, Yechen Jin, Zhen Li +5
Text-based speech editing aims to modify specific segments while preserving speaker identity and acoustic context. Current approaches generally involve either expensive task-specif…
Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
Yuntai Bao, Xuhong Zhang, Jintao Chen +7
Intervention-based model steering offers a lightweight and interpretable alternative to prompting and fine-tuning. However, by adapting strong optimization objectives from fine-tun…
Ground What You See: Hallucination-Resistant MLLMs via Caption Feedback, Diversity-Aware Sampling, and Conflict Regularization
Miao Pan, Wangjie Gan, Jintao Chen +4
While Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse tasks, their practical deployment is severely hindered by hallucination issues, which…
ToolGate: Contract-Grounded and Verified Tool Execution for LLMs
Yanming Liu, Xinyue Peng, Jiannan Cao +5
Large Language Models (LLMs) augmented with external tools have demonstrated remarkable capabilities in complex reasoning tasks. However, existing frameworks rely heavily on natura…