13 papers
How Data Scales in Agentic Reinforcement Learning: Laws and Synthesis Strategies
Bowei He, Yankai Chen, Xiaokun Zhang +4
Pretraining scaling laws treat training data as a one-dimensional quantity: a token count. Agentic reinforcement learning (RL) inherits this scalar abstraction, but modern synthesi…
Discrete Diffusion Models: A Unified Framework from Tokenization to Generation
Ye Yuan, Weien Li, Rui Song +20
Discrete denoising diffusion models (DDMs) have recently emerged as a compelling alternative to autoregressive (AR) modeling for discrete data, offering parallel generation and ite…
Overview of FinMMEval 2026 Task 2: Multilingual Financial Short-Answer Question Answering
Zhuohan Xie, Xueqing Peng, Georgi Georgiev +18
FinMMEval 2026 Task 2 evaluates short-answer financial question answering over multilingual evidence. Each final-test item pairs an English question with financial statements and n…
Overview of FinMMEval 2026 Task 1: Multilingual Financial Multiple-Choice Question Answering
Zhuohan Xie, Yuyang Dai, Rania Elbadry +18
FinMMEval 2026 Task 1 evaluates multilingual financial multiple-choice question answering in English, Chinese, Arabic, and Hindi. The task tests whether systems can select the corr…
JT-SAFE-V2: Safety-by-Design Foundation Model with World-Context Data
Junlan Feng, Fanyu Meng, Chong Long +12
We introduce JT-Safe-V2, a large language model designed to advance the safety and trustworthiness of foundation models, extending our previous JT-Safe model toward a more comprehe…
MINER: Mining Multimodal Internal Representation for Efficient Retrieval
Weien Li, Rui Song, Zeyu Li +8
Visual document retrieval has become essential for accessing information in visually rich documents. Existing approaches fall into two camps. Late-interaction retrievers achieve st…
QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents
Ye Yuan, Rui Song, Weien Li +12
Social deduction games have become a popular testbed for probing reasoning, deception, coordination, and belief modeling in Large Language Model (LLM) agents. However, most environ…
Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization
Weixu Zhang, Ye Yuan, Changjiang Han +7
Large Language Models (LLMs) exhibit strong implicit personalization ability, yet most existing approaches treat this behavior as a black box, relying on prompt engineering or fine…
LLM Safety From Within: Detecting Harmful Content with Internal Representations
Difan Jiao, Yilun Liu, Ye Yuan +4
Guard models are widely used to detect harmful content in user prompts and LLM responses. However, state-of-the-art guard models rely solely on terminal-layer representations and o…
Beyond Message Passing: A Semantic View of Agent Communication Protocols
Dun Yuan, Fuyuan Lyu, Ye Yuan +11
Agent communication protocols are becoming critical infrastructure for large language model (LLM) systems that must use tools, coordinate with other agents, and operate across hete…
CARE: Privacy-Compliant Agentic Reasoning with Evidence Discordance
Haochen Liu, Weien Li, Rui Song +6
Large language model (LLM) systems are increasingly used to support high-stakes decision-making, but they typically perform worse when the available evidence is internally inconsis…
Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization
Linfeng Du, Ye Yuan, Zichen Zhao +8
Large language models (LLMs) excel at general-purpose tasks, yet adapting their responses to individual users remains challenging. Retrieval augmentation provides a lightweight alt…
Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection
Zhiwei Liu, Yupen Cao, Yuechen Jiang +22
Large language models (LLMs) have been widely applied across various domains of finance. Since their training data are largely derived from human-authored corpora, LLMs may inherit…