arXiv:2605. 26874v2 Announce Type: replace-cross Abstract: LLM-based agents for industrial asset operations show limited accuracy when reasoning over flat document stores.
By Madhulatha Mandarapu, Sandeep Kunkunuru
arXiv:2606. 01279v1 Announce Type: new Abstract: AI agents are increasingly being tasked with automating AI research itself, particularly the critical post-training phase that transforms base LLMs into aligned assistants.
By Zhengyang Zhao, Shengjie Ye, Lu Ma, Hao Liang, Hengyi Feng, Wentao Zhang
arXiv:2606. 01314v1 Announce Type: new Abstract: Recent self-evolving agents have shown that skills can be discovered, refined, and accumulated through execution.
By Yangbo Wei, Zhen Huang, Shaoqiang Lu, Junhong Qian, Qifan Wang, Chen Wu, Lei He
arXiv:2606. 01199v1 Announce Type: new Abstract: Large language agents are increasingly used for social simulation, yet it remains unclear whether they can sustain coherent behavior in structured organizations, where goals must propagate through hierarchy, tasks depend on prior execution, and artifacts accumulate over long horizons.
By Xuancheng Zhu, Yang Yue, Shuaibing Wan, Zihan Dou, Xiaohan Zhang, Yongrui Liu, Guoshun Nan
arXiv:2606. 00880v1 Announce Type: cross Abstract: Continual reinforcement learning aims to produce agents that learn not only to improve at their current tasks but also to adapt as task distributions change.
By Purab Seth, Neil Shah, Kunal Jha, Samuel J. Gershman, Max Kleiman-Weiner, Wilka Carvalho
arXiv:2606. 00555v1 Announce Type: new Abstract: Structure-based drug design increasingly employs LLM agents to iteratively refine ligands against a target pocket, yet a viable ligand must satisfy two often-conflicting objectives -- binding affinity and druggability -- which single optimization steps rarely improve together.
By Zaifei Yang, Weiyu Chen, Yaqing Wang, James Kwok
arXiv:2606. 00708v1 Announce Type: new Abstract: Automated data science is a structured model-selection problem.
By Yifan Bao, Xinyu Xi, Xinyu Liu, Wen Ge, Lei Jiang, Kevin Zhang, Raad Khraishi, Yihao Ang, Anthony K. H. Tung, Lukasz Szpruch, Hao Ni
ReAct-style LLM agents often rediscover the same reasoning routines across problems, yet leave those routines trapped in transient scratchpads. We introduce Reasoning Primitive Induction, a single-pass method that mines successful ReAct traces, clusters recurrent reasoning moves, and converts the most frequent moves into a compact library of typed pseudo-tools.
Text files such as skill files, memory files, and behavioral configuration files play a central role in defining how modern agents act. Through edits by humans or the agents themselves, these files may evolve over time, directly steering the agent's behavior in future interactions.
Agentic systems entering production typically operate as partially integrated assemblies where structural defects, not task-level errors, dominate the failure landscape. At this maturity level, task-level error detection may be infeasible: structural failure modes mask the signal that task-level monitors are designed to detect.
Enabling Vision-Language Models (VLMs) to perform spatial reasoning remains challenging. Existing approaches treat VLMs as passive observers, which is difficult for real-world applications.
Why Agentic BI threatens an entire profession The post Escaping the Valley of Choice in BI appeared first on Towards Data Science .
By Hugo Lu
Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites. Despite rapid progress, the strongest systems remain largely proprietary, while open agents still depend heavily on supervised post-training over large collections of curated web trajectories.
Large language model-driven multi-agent systems enhance the reliability of complex reasoning tasks through multi-round deliberation, role specialization, and cross-validation. However, existing multi-agent debate and collaboration frameworks typically adopt fully connected communication, causing the number of messages, token costs, and end-to-end latency to grow approximately quadratically with the number of agents; although fixed sparse topologies reduce overhead, they cannot adapt communication relationships to different task instances or intermediate reasoning states, making them prone either to preserving low-value interactions or to losing critical error-correction information.
As generative platforms such as Suno and Udio reach human-grade audio quality, the scope of AI's utility has expanded across the entire music production workflow. Beyond simple track generation, these advancements have catalyzed the adoption of AI-driven methodologies in diverse forms.
Test-time scaling has become a major way to improve large language model reasoning, but its orchestration has remained designer-engineered: a fixed sample budget, a fixed refinement loop, a fixed scoring rule, or a fixed search policy decides how compute is spent, leaving the model in charge of solving but not of orchestration. We introduce ATLAS, an agentic test-time scaling framework in which an LLM orchestrator owns the control loop end-to-end.
Large language models excel at general tasks but underperform smaller supervised models in specialized, high-stakes domains where training labels are costly. We address this regime with EvoPool, an evolutionary multi-agent framework inspired by Darwinian evolution.
Traditional operating systems were designed around deterministic programs, explicit control flow, and human initiated workflows. Their core abstractions processes, threads, system calls, files, and permissions assume bounded behavior and predictable interaction patterns.
The unified agent for long-horizon productivity and coding, launching with Work and Code modes. Plus, a new Vibe VS Code extension.