Distilling long-chain reasoning trajectories from large teacher models provides an effective way to improve the reasoning ability of small language models. However, existing methods typically select a fixed training set before distillation, overlooking that the usefulness of a reasoning example changes as the student e...
Jia-Ming Su, Suorong Yang, Xu-Dong Li et al.· 0 citations
Large language model (LLM) agents are highly vulnerable to memory-poisoning attacks. Existing defenses primarily rely on external modules for either static memory isolation or continuous online auditing, resulting in low memory efficiency and high computational overhead. To address these limitations, inspired by neuros...
Lei Liu, Yunji Liang, Xiaowen Zhang et al.· 0 citations
Long-horizon autonomous research has shown promise in accelerating scientific progress through sustained cycles of hypothesis generation, implementation, and validation. However, this Generate-Execute-Feedback paradigm relies on reactive trial-and-error, where costly and time-consuming executions introduce severe feedb...
Meng-Di Liu, Cheng-Hao Jia, Hong Chang et al.· 0 citations
While reinforcement learning with verifiable reward (RLVR) enhances reasoning in large language models, its efficacy in long-horizon multimodal tasks remains underexplored. Visual Sudoku puzzles pose a representative challenge, requiring multi-step deductive reasoning over both local constraints and global dependency c...
Sida Li, Yuanxin Liu, Linli Yao et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
World models enable large language model (LLM) agents to anticipate action effects and make informed decisions. For generalization, it is desirable for such world models to transfer efficiently to new environments with similar interaction structure and underlying dynamics. Recent approaches encode world dynamics as sym...
Open coding agents are commonly trained through supervised fine-tuning on interaction trajectories whose final patches pass the benchmark test suite. However, this outcome-level filtering criterion ignores process quality: trajectories that eventually succeed may still contain inefficient interaction patterns such as r...
Sida Li, Yuanxin Liu, Shicheng Li et al.· 0 citations
Large language models (LLMs) increasingly generate structured layouts and executable scene programs from natural-language instructions. However, executability does not imply engineering feasibility: an industrial scene program may execute successfully while its final state still violates coupled boundary, collision, cl...
Fuqiang Wang, Zheng Guo, Xiaoming Wu et al.· 0 citations
LLM-based multi-agent systems (MAS) have emerged as a promising paradigm for enhancing complex reasoning through role specialization and collaboration, yet a key challenge remains: how can collaboration be adapted to a backbone's competence on the current query? This problem matters because more collaboration is not al...
Song-Miao Wang, Yu-Cheng Wang, Cheng-Lin Yu et al.· 0 citations
LLM-as-a-Service has become a dominant paradigm for accessing large language models without requiring local deployment. However, the process raises severe privacy concerns when user queries may include sensitive or confidential contexts. Differential privacy (DP) provides a principled approach to protecting such inputs...
Zhihao Liu, Yitian Cheng, Shuang Liu et al.· 0 citations
A new graph-constrained generative paradigm is introduced, Anticipatory Generative Modeling, which resolves next transition selection by incorporating the Anticipation of how the future route may unfold toward the destination, and a novel generative model named Foresight that formulates a probabilistic model for an"ant...
Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-augmented agents give one model both kinds of tools and let it schedule itself. We present KnowForge, a pipeline separated by job: a hybrid-retrieval knowledge-point in...
As large language models (LLMs) acquire advanced biological design capabilities, they offer substantial research benefits but simultaneously introduce severe dual-use risks, such as engineering enhanced pathogens or drug-resistant bacteria. While biosecurity frameworks recognize these threats, the actual risk of LLMs e...
Yu-Zhen Wang, Chun-Xiao Li, Bai-Chen Le et al.· 0 citations
