16 papers
The Butterfly Effect in LLM Social Simulations: From Architecture Sensitivity to Robustness Audits
Jinyi Ye, Lei Cao, Ding Chen +1
A butterfly effect occurs when a local perturbation propagates through a system and produces divergence in its collective outcome. In LLM social simulations, this creates a particu…
SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback
Leo Luo, Haining Xie, Siqi Shen +8
Text-to-SQL on complex schemas is unreliable on a single pass, so recent systems generate multiple SQL candidates and let voting filter out errors. Yet voting alone is not enough,…
GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic Manipulation
Boxiang Qiu, Liliang Chen, Yue Liao +12
We introduce GE-Sim 2.0 (Genie Envisioner World Simulator 2.0), a closed-loop video world simulator for robotic manipulation. Building on the action-conditioned video generation fr…
Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement
Dingwei Chen, Zefang Zong, Zhipeng Ma +5
Agentic reinforcement learning (RL) has proven effective for training LLM-based agents with external tool-use capabilities. However, we identify that agentic RL training induces in…
StepAudio 2.5 Technical Report
Bin Lin, Bo Zhao, Boyong Wu +98
Unified audio-language modeling has emerged as a prominent trend in modern speech systems, promising to bring the reasoning capabilities of large language models to auditory tasks.…
Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits
Jinyi Ye, Lei Cao, Ding Chen +1
The scientific claims drawn from LLM social simulations should be no stronger than the robustness audits that support them. Generative agents bring new expressive power to agent-ba…
MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval
Chunyu Li, Mengyuan Zhang, Jingyi Kang +6
In agent memory systems, the reranking model serves as the critical bridge connecting user queries with long-term memory. Most systems adopt the "retrieve-then-rerank" two-stage pa…
ATGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping
Dingwei Chen, Zefang Zong, Zhipeng Ma +5
Reinforcement learning for agentic large language models (LLMs) typically relies on a sparse, trajectory-level outcome reward, making it difficult to evaluate the contribution of i…
From Context to Skills: Can Language Models Learn from Context Skillfully?
Shuzheng Si, Haozhe Zhao, Yu Lei +10
Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly lear…
Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering
Chak Tou Leong, Dingwei Chen, Heming Xia +4
Large reasoning models (LRMs) have achieved remarkable success in complex problem-solving, yet they often suffer from computational redundancy or reasoning unfaithfulness. Current…
ATPO: Agentic Turn-based Policy Optimization via Tree Search
Zefang Zong, Dingwei Chen, Yang Li +6
LLM agents have emerged as powerful systems for tackling multi-turn tasks by interleaving internal reasoning and external tool interactions. Agentic Reinforcement Learning has rece…
CTR-Sink: Attention Sink for Language Models in Click-Through Rate Prediction
Zixuan Li, Binzong Geng, Jing Xiong +11
Click-Through Rate (CTR) prediction, a core task in recommendation systems, estimates user click likelihood using historical behavioral data. Modeling user behavior sequences as te…
Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation
Dingwei Chen, Ziqiang Liu, Feiteng Fang +6
Large Language Models (LLMs) demonstrate remarkable capabilities in text understanding and generation. However, their tendency to produce factually inconsistent outputs, commonly r…
Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity
Feiteng Fang, Dingwei Chen, Xiang Huang +10
Currently, most reinforcement learning tasks focus on domains like mathematics and programming, where verification is relatively straightforward. However, in subjective tasks such…
Lower Layers Matter: Alleviating Hallucination via Multi-Layer Fusion Contrastive Decoding with Truthfulness Refocused
Dingwei Chen, Feiteng Fang, Shiwen Ni +6
Large Language Models (LLMs) have demonstrated exceptional performance across various natural language processing tasks. However, they occasionally generate inaccurate and counterf…
Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Models
Shiwen Ni, Dingwei Chen, Chengming Li +3
Recent advancements in Large Language Models (LLMs) have showcased their remarkable capabilities in text understanding and generation. However, even stronger LLMs are susceptible t…