Get started
Author

Yixin Cao

Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks
2026 · Yuan, Hongbang, Jin, Zhuoran, et al. · arXiv (Cornell University)
PDF
From Concentration to Differentiation and Back: Routing Effective Rank in MoE Reasoning Cohorts
2026 · Chen, Kang, Zhao, Sihan, et al. · arXiv (Cornell University)
PDF
Disagree to Explore, Agree to Commit: Routing-Guided Test-Time Scaling for Software Agents
2026 · Chen, Kang, Nian, Junjie, et al. · arXiv (Cornell University)
PDF
Beyond the Trace: Coupling an Interpretable Reasoning-State Readout to Native MoE Routing
2026 · Chen, Kang, Zhao, Sihan, et al. · arXiv (Cornell University)
PDF
Does the Same Token Mean the Same State? MoE Routing as Signal for Reasoning Control
2026 · Chen, Kang, Yu, Minshen, et al. · arXiv (Cornell University)
PDF
TraceGraph: Shared Decision Landscapes for Diagnosing and Improving Agent Trajectories
2026 · Nian, Junjie, Chen, Kang, et al. · arXiv (Cornell University)
PDF
SliceGraph: Mapping Process Isomers in Multi-Run Chain-of-Thought Reasoning
2026 · Chen, Kang, Nian, Junjie, et al. · arXiv (Cornell University)
PDF
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
2026 · Li, Xiao, Zheng, Xiang, et al. · arXiv (Cornell University)
PDF
Reinforcement Learning with Conditional Expectation Reward
2026 · Xiao, Changyi, Xu, Caijun, et al. · arXiv (Cornell University)
PDF
GAM-RAG: Gain-Adaptive Memory for Evolving Retrieval in Retrieval-Augmented Generation
2026 · Wang, Yifan, Jiang, Mingxuan, et al. · arXiv (Cornell University)
PDF
NEX: Neuron Explore-Exploit Scoring for Label-Free Chain-of-Thought Selection and Model Ranking
2026 · Chen, Kang, Feng, Zhuoka, et al. · arXiv (Cornell University)
PDF
Thinking Traps in Long Chain-of-Thought: A Measurable Study and Trap-Aware Adaptive Restart
2026 · Chen, Kang, Yu, Fan, et al. · arXiv (Cornell University)
PDF
ARM: Role-Conditioned Neuron Transplantation for Training-Free Generalist LLM Agent Merging
2026 · Zhuoka Feng, Kang Chen, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
From Correctness to Utility: Gain-Based Prefix Evaluation for LLM Reasoning
2026 · Yuhang Zhou, Yixin Cao, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
HarmProfile: Characterizing Harmful Distributions in Frontier LLMs
2026 · Zhouyuan Ma, Yutao Wu, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
From Base Rollouts to RL Reasoning: A Budgeted Search Perspective
2026 · Wenhe Sun, Cunxiang Wang, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Works count: 16
Citation count:
H-index:
I10-index:
Year
Topic
Type