Large language models achieve strong reasoning performance, but often at prohibitive training cost - a challenge that is especially acute for compact models ($\leq 4 \, \mathrm{B}$ parameters) trained under limited budgets. We introduce MADA-RL, a post-training framework that specializes compact models into generator and critic roles and trains them with a debate-aware learning signal, fine-tuning only a small subset of parameters via LoRA adapters.
Self-hosted AI agents read and write their own memory and configuration files to function. An agent may get compromised via corruption of its own state -- a compromise realized via legitimate OS system call invocation.
Large language models (LLMs) can assist GPU kernel generation, but their practical effectiveness depends on whether generated code can be reliably constrained, validated, profiled, and selected. This paper presents a harness-centered system for LLM-driven GPU kernel optimization in the MLSys 2026 FlashInfer AI Kernel Generation Contest on NVIDIA Blackwell B200 GPUs.
Most reinforcement learning controllers for these networks assume stationary conditions, and the few that handle change react to the external environment while leaving the network's internal state unexamined. We show that sustained non-stationarity damages this internal state directly: as objectives shift, neurons progressively fall dormant and the shared policy loses the capacity to learn.
LLM-based autonomous agents require external memory to overcome their statelessness and limited context window for long-term interaction and dynamic knowledge reasoning. However, existing memory retrieval methods often lack adaptability and sample efficiency, and struggle to retrieve the right mixture of memories from heterogeneous stores.
Inverse reinforcement learning (IRL) provides a powerful framework for learning from demonstrations. However, real-world tasks often exhibit substantial natural variations (e.
Coordinating payload transfers between subsystems is a critical challenge in lifelong Multi-Agent Pickup and Delivery (MAPD). We study systems where agents are confined to separate regions and must exchange payloads through shared handover stations.
User experience is a first-class objective in industrial e-commerce recommender systems (RS). Post-ranking strategies, which govern diversity, similarity, and exposure over a ranked list, are widely deployed in industrial RS for their simplicity and low serving cost.
Verify-repair loops are a standard means for large language model (LLM) agents to correct faulty plans in code generation, mathematical reasoning, and tool use. When both the verifier and the repairer are noisy, repair can damage already-correct plans, and reported acceptance keeps rising while true validity falls, so existing methods lack a principled basis for deciding when repair should stop.
arXiv:2604. 06742v2 Announce Type: replace-cross Abstract: The evolution of Large Language Models (LLMs) has catalyzed a paradigm shift towards intent-driven software development, where autonomous agents are expected to design and deliver complete, runnable software systems from scratch.
By Ruida Hu, Xinchen Wang, Chao Peng, Cuiyun Gao, David Lo
arXiv:2607. 15388v1 Announce Type: new Abstract: Many math- and science-oriented agent systems use hierarchical designs with specialized reviewer roles, assuming that a dedicated review stage should help turn wrong candidates into correct ones.
By Chih-Hsuan Yang, Jingyan Jiang, Vikram Vasudevan, Cheng-Hau Yang, Huihuo Zheng, Le Chen, Eliu A. Huerta, Venkatram Vishwanath, Ian T. Foster, Rajeev Thakur
arXiv:2607. 15883v1 Announce Type: cross Abstract: Large language models are broadly capable, yet in sustained one-to-one conversation they still read as flat: competent, responsive, and somehow not quite the presence of a mind.
By Sebastian Cochinescu
arXiv:2607. 15509v1 Announce Type: cross Abstract: We present a fully automated closed-loop AutoML framework that uses GPT-5, GPT-4o, and Claude Sonnet 4 as autonomous neural architecture designers for cross-lingual handwritten optical character recognition.
By Mobina Kashaniyan, Amirhossein Ghassemi, Nasser Mozayani
arXiv:2607. 15657v1 Announce Type: cross Abstract: Multimodal AI agents increasingly rely on persistent long-term memory to ground generation in past visual and textual episodes.
By Halima Bouzidi, Mboutidem Ekemini Mkpong, Mohammad Abdullah Al Faruque
arXiv:2607. 15280v1 Announce Type: new Abstract: Sequential diagnosis requires balancing diagnostic accuracy against resource costs through iterative information gathering.
By Shaoting Tan, Ning Liu, Yuntao Du, Shuyue Wei, Wu Shuai, Qian Li, Yanyu Xu, Wei Zhang, Lizhen Cui, Haitao Yuan
arXiv:2607. 15935v1 Announce Type: cross Abstract: Deep reinforcement learning (DRL) has a longstanding tradition in addressing the reach-avoid task problem, especially for controlling robotic arms.
By Jonas Weihing, Shahram Eivazi
arXiv:2607. 15697v1 Announce Type: cross Abstract: Backdoor attacks pose a critical threat to neural network models, allowing attackers to implant a backdoor during the training phase by manipulating a small portion of the training data.
By Jinwen Xin, Xixiang Lv
arXiv:2607. 15282v1 Announce Type: cross Abstract: Empathy is most often theorized as resonance: a mirroring of another's present emotional or cognitive state.
By Molood Arman
arXiv:2607. 15901v1 Announce Type: new Abstract: Despite strong capabilities in data understanding and decision-making, autonomous data science agents still heavily rely on trial-and-error workflows that involve expensive computation.
By Zherui Yang, Fan Liu, Hao Liu
arXiv:2512. 24069v2 Announce Type: replace Abstract: We consider the design of mixing matrices to minimize the operation cost for decentralized federated learning (DFL) in wireless networks, with focus on minimizing the maximum per-node energy consumption.
By Xusheng Zhang, Tuan Nguyen, Ting He