collaborators

35 papers

cs.LG2026

HSD: Hybrid Hindsight Self-Distillation

Qiye Cai, Yichuan Ma, Linyang Li +7

Reinforcement learning with verifiable rewards (RLVR) provides reliable outcome supervision for language model reasoning, but a scalar trajectory reward offers limited token-level…

cs.CL2026

Large Language Model Agents Are Not Always Faithful Self-Evolvers

Weixiang Zhao, Yingshuo Wang, Yichen Zhang +5

Self-evolving large language model (LLM) agents continually improve by accumulating and reusing past experience, yet it remains unclear whether they faithfully rely on that experie…

cs.LG2026

SL-BiLEM: Structured Learnable Behavior-in-the-Loop Epidemic Modeling for Forecasting and Policy Evaluation

Haochun Wang, Sendong Zhao, Jingbo Wang +3

Epidemic forecasting faces a fundamental challenge: human behavior dynamically responds to disease spread, creating feedback loops that induce distribution shifts at policy interve…

cs.AI2026

DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning

Yang He, Xiao Ding, Bibo Cai +5

Tool-Integrated Reasoning (TIR) extends LLM capabilities by leveraging external environments. However, existing methods lack the deliberation during sequential tool invocation requ…

cs.CL2026

Easier to Judge than to Find: Predicting In-Context Learning Success for Demonstration Selection

Haochun Wang, Chaofen Yang, Jiatong Liu +5

In-context learning (ICL) is highly sensitive to which demonstrations appear in the prompt, but selecting them is expensive because the space of possible demonstration contexts and…

cs.AI2026

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction

Jiahe Guo, Xiangran Guo, Jiaxuan Chen +6

Multimodal large language models (MLLMs) often fail to transfer safety capabilities learned in the text modality to semantically equivalent non-text inputs, revealing a persistent…