11 papers
Gradients Know What Outcomes Don't: Unlocking Reinforcement Learning for LLM Reasoning with Gradient-Aligned Rewards
Leqi Zheng, Jinbo Su, Fang Niu +8
Reinforcement learning from verifiable rewards (RLVR) drives chain-of-thought reasoning in large language models, yet its binary outcome reward cannot distinguish among correct tra…
SciLENS: RL-Driven Autonomous Agents for Scientific Localized Evidence Navigation and Synthesis
Leqi Zheng, Jinbo Su, Yuying Li +10
Scientific literature synthesis agents increasingly rely on proprietary online services, limiting reproducibility, privacy, and offline deployment. To address this challenge, we in…
JPO: Juris Policy Optimization for Structured Legal Reasoning in Criminal Judgment Prediction
Zhaolu Kang, Yantao Liu, Tailong Luo +14
Criminal judgment prediction requires models to infer statutory articles, charges, and sentencing outcomes from case facts. Unlike standard classification tasks, it involves a stru…
EDIS: Diagnosing LLM Reasoning via Entropy Dynamics
Chenghua Zhu, Siyan Wu, Xiangkang Zeng +6
Entropy-based confidence signals are increasingly leveraged to improve reasoning in large language models (LLMs), yet existing approaches treat confidence as a static quantity -- t…
Multimodal Multi-Agent Empowered Legal Judgment Prediction
Zhaolu Kang, Junhao Gong, Qingxi Chen +7
Legal Judgment Prediction (LJP) aims to predict the outcomes of legal cases based on factual descriptions, serving as a fundamental task to advance the development of legal systems…
Conflict-Aware Client Selection for Multi-Server Federated Learning
Mingwei Hong, Zheng Lin, Zehang Lin +7
Federated learning (FL) has emerged as a promising distributed machine learning (ML) that enables collaborative model training across clients without exposing raw data, thereby pre…
WebCryptoAgent: Agentic Crypto Trading with Web Informatics
Ali Kurban, Wei Luo, Liangyu Zuo +5
Cryptocurrency trading increasingly depends on timely integration of heterogeneous web information and market microstructure signals to support short-horizon decision making under…
When Helpers Become Hazards: A Benchmark for Analyzing Multimodal LLM-Powered Safety in Daily Life
Xinyue Lou, Jinan Xu, Jingyi Yin +8
As Multimodal Large Language Models (MLLMs) become an indispensable assistant in human life, the unsafe content generated by MLLMs poses a danger to human behavior, perpetually ove…
FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning
Yujie Feng, Hao Wang, Jian Li +6
Continual learning (CL) for large language models (LLMs) aims to enable sequential knowledge acquisition without catastrophic forgetting. Memory replay methods are widely used for…
Beyond N-grams: A Hierarchical Reward Learning Framework for Clinically-Aware Medical Report Generation
Yuan Wang, Shujian Gao, Jiaxiang Liu +6
Automatic medical report generation can greatly reduce the workload of doctors, but it is often unreliable for real-world deployment. Current methods can write formally fluent sent…
ReasonAct: Progressive Training for Fine-Grained Video Reasoning in Small Models
Jiaxin Liu, Zhaolu Kang
While recent multimodal models have shown progress in vision-language tasks, small-scale variants still struggle with the fine-grained temporal reasoning required for video underst…