…Across four customer-service domains and a mixed panel of open- and closed-weight models, Ledger Agent improves average passk over a standard prompt-based tool-calling approach, with the largest gains…
…Xucong Wang , , , , , , Abstract Role-Agent framework enables LLM agents to function as both agent and environment through bootstrapped co-evolution, improving performance via environment-aware reasoning and targeted practice. Generated by Qwen…
…We present the Local Communication for Multi-agent Pathfinding (LC-MAPF), a generalizable pre-trained model that applies multi-round communication between neighboring agents to exchange information and improve their coordination. Our…
…Yuxiang Ji , , , , , , , , Abstract Agentic reinforcement learning for large language models leverages action data from human interactions as reference guidance to improve exploration and reduce dependence on costly supervised fine-tuning. AI-generated…
…View arXiv page View PDF GitHub 29 Add to collection Community We are excited to share T²PO, an uncertainty-guided exploration control method for stable multi-turn agentic reinforcement learning. T²PO improves…
…Zhao on Jun 2 Authors: , Hui Chen , , Abstract FineVerify is a self-verification framework for agentic search that improves accuracy through decomposed sub-question checking and trajectory selection. Generated by Qwen/Qwen2…
…Ziheng Li , , , , Abstract A self-supervised training framework called MemTrain enhances long-horizon language model agents' memory capabilities through proxy tasks optimized via GRPO, improving downstream reasoning performance. Generated by Qwen/Qwen2…
…To isolate memory assessment, the questions must be answered using only the agent's memory, without access to raw video. Built on Qwen3-VL-30B-A3B , TaskMem improves VQA accuracy by 6…
…source framework for training advanced multimodal search agents using reinforcement learning, featuring specialized data curation, diverse tool environments, and a novel training algorithm that improves performance across multiple benchmarks. AI-generated summary…
…Heming Zou , , , , , , , , , , , Abstract TRACE is a rollout allocation framework that improves reward contrast in multi-turn agentic reinforcement learning by dynamically distributing resources across tree-structured rollouts based on prefix-level informativeness…