Shijie Tang
Author directory2026
Models Know Their Shortcuts: Deployment-Time Shortcut Mitigation
Jiayi Li | Shijie Tang | Gün Kaynar | Shiyi Du | Carl Kingsford
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Jiayi Li | Shijie Tang | Gün Kaynar | Shiyi Du | Carl Kingsford
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Pretrained text encoders are prone to shortcut learning, relying on token-label correlations that fail once the distribution shifts in deployment. Existing shortcut mitigation methods mainly operate at training time and assume access to training data, training dynamics, or shortcut annotations, which are hardly available during deployment, where only the converged model remains. We show that this model alone suffices to mitigate shortcuts during deployment: a biased model internalizes a signal of its learned shortcuts that can be captured via unsupervised gradient-based attribution. We further prove that deployment-time mitigation is information-theoretically upper-bounded by training-time mitigation. Nevertheless, exploiting this gradient signal, our proposed unsupervised deployment-time shortcut mitigation framework for pretrained text encoders, Shortcut Guardrail, recovers substantial performance under shortcut distribution shift, matching or outperforming training-time baselines across sentiment classification, toxicity detection, and natural language inference.
2025
SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligence
Yao Zhang | Chenyang Lin | Shijie Tang | Haokun Chen | Shijie Zhou | Yunpu Ma | Volker Tresp
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Yao Zhang | Chenyang Lin | Shijie Tang | Haokun Chen | Shijie Zhou | Yunpu Ma | Volker Tresp
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
The rapid progress of Large Language Models has advanced agentic systems in decision-making, coordination, and task execution. Yet, existing agentic system generation frameworks lack full autonomy, missing from-scratch agent generation, self-optimizing agent functionality, and collaboration, limiting adaptability and scalability. We propose SwarmAgentic, the first framework that fully automates agentic system generation, optimization, and collaboration, constructing agents from scratch and jointly refining functionality and coordination via language-driven exploration. To enable efficient search over system-level structures, SwarmAgentic maintains a population of candidate systems and evolves them via feedback-guided updates, drawing inspiration from Particle Swarm Optimization (PSO). We evaluate our method on six real-world, open-ended, and exploratory tasks involving high-level planning, system-level coordination, and creative reasoning. Given only a task description and an objective function, SwarmAgentic outperforms all baselines, achieving a +261.8% relative improvement over ADAS on the TravelPlanner benchmark, highlighting the effectiveness of full automation in structurally unconstrained tasks. This framework marks a significant step toward scalable and autonomous agentic system design, bridging swarm intelligence with fully automated system multi-agent generation.
Search