Papers
CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents
Jiayu Liu, Cheng Qian, Zhaochen Su et al.
Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
Sikuan Yan, Xiufeng Yang, Zuchao Huang et al.
Mathematical Proof as a Litmus Test: Revealing Failure Modes of Advanced Large Reasoning Models
Dadi Guo, Jiayu Liu, Zhiyuan Fan et al.
LLM-as-Scheduler: Agentic Workflow Dynamic Scheduling
Dawei Xiang, Kexin Chu, Wenyan Xu et al.
UR2 : Unify RAG and Reasoning through Reinforcement Learning
Weitao Li, Boran Xiang, Xiaolong Wang et al.
From Form to Logic: Masked Reconstruction and Reasoning Distillation for Short Video Fake News Detection
Qingyan Wang, Lianwei Wu, Botao Wang et al.
A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement
Shengji Tang, Jianjian Cao, Weihao Lin et al.
No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning
Zhicong Li, Lingjie Jiang, Yulan Hu et al.
Probing for Reading Times
Eleftheria Tsipidi, Samuel Kiegeland, Francesco Ignazio Re et al.
Generative Gamer: Learning Equilibrium Strategy by LLM-driven Dynamic Deduction
Yadong Zhang, Xinshu Shen, Yupei Ren et al.
AgentMark: Utility-Preserving Behavioral Watermarking for Agents
Kaibo Huang, Jin Tan, Yukun Wei et al.
The Bidirectional Process Reward Model
Lingyin Zhang, Jun Gao, Xiaoxue Ren et al.
Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters
Zhiyu Xu, Lean Wang, Yuanxin Liu et al.
Mock Worlds, Real Skills: Building Small Agentic Language Models with Synthetic Tasks, Simulated Environments, and Rubric-Based Rewards
Yuanjie Lyu, Chengyu Wang, Lei Shen et al.
GASim: A Graph-Accelerated Hybrid Framework for Social Simulation
Xuan Zhou, Yanhui Sun, Hantao Yao et al.
Deriving Character Logic from Storyline as Codified Decision Trees
Letian Peng, Kun Zhou, Longfei Yun et al.
Reward Modeling for Scientific Writing Evaluation
Furkan Şahinuç, Subhabrata Dutta, Iryna Gurevych
WeightLoRA: Keep Only Necessary Adapters
Andrey Veprikov, Vladimir Solodkin, Zyl Alexander et al.
Multilingual Idioms in Sentences and Conversations Across High-, Medium-, and Low-Resource Languages
Saeed Almheiri, Bilal Elbouardi, Salsabila Zahirah Pranida et al.
PRISM: Probabilistic Reward Model with Inherent Structural Modeling
Yuhang Zhou, Yixin Cao, Yuchen Ni et al.
PDR: A Plug-and-Play Positional Decay Framework for LLM Pre-training Data Detection
Jinhan Liu, Yibo Yang, Ruiying Lu et al.
Capability Decomposition for Unified Information Extraction via Hierarchical Mixture-of-Experts
Jing Zhou, Peng Wang, Wenjun Ke et al.
Reasoning Gets Harder for LLMs Inside A Dialogue
Ivan Kartáč, Mateusz Lango, Ondrej Dusek