The paper investigates two strategies for improving large language model (LLM) evaluation: specialized judge weights and rule‑based deferral policies. Experiments on nearly 100,000 rubric‑conditioned samples show that correct rubrics boost accuracy, while incorrect ones hurt it, and that splitting training data into criterion‑specific experts can severely degrade performance unless the experts are warm‑started from a unified model. The authors demonstrate that lightweight deferral cascades can match or exceed the accuracy of larger standalone judges at a fraction of the compute cost, and they provide practical design rules for building efficient, reliable LLM evaluators.
By Ye Chen, Weining Zhang
The paper introduces a method to improve test-time scaling (TTS) for large language models by using multi-agent systems (MAS) to split long reasoning chains into manageable contexts. A new dataset, M500, containing 500 multi-agent collaborative reasoning traces, is used to fine‑tune open‑source models, enabling them to learn collaborative patterns and outperform their base versions. An adaptive scaling strategy with a "CEO" agent is proposed to dynamically guide reasoning depth, and experiments in the AgentVerse framework confirm the effectiveness of the approach.
By Can Jin, Hongwu Peng, Qixin Zhang, Yujin Tang, Dimitris N. Metaxas, Tong Che
Tree-of-Experience (ToE) is a hierarchical experience-management framework designed for large language model agents that aligns stored experiences with the agents’ reasoning hierarchy. By organizing experiences into a shared tree of analytical perspectives and reasoning paths, ToE calibrates reliability through environmental outcomes, enabling systematic updating, cross-task transfer, and efficient retrieval. Experiments on Game of 24 and FinEvolveBench demonstrate that ToE yields significant performance gains—31.4% accuracy improvement on Game of 24 and a 41.24% average improvement in tsIC on FinEvolveBench—outperforming both experience-free baselines and conventional experience-management methods.
By Zihao Deng, Yining Zhu, Leiming Wang, Junbo Wang, Jingfei Lu
BIPPO (Budget-aware Independent Proximal Policy Optimization) is a multi‑agent reinforcement learning framework designed for energy‑efficient client selection in federated learning (FL) over IoT systems. It addresses infrastructure constraints such as limited resources and device churn, which traditional FL and RL approaches overlook. Evaluated on two image‑classification tasks with non‑IID data, BIPPO improves mean accuracy over non‑RL methods, standard PPO, and IPPO while consuming only a negligible portion of the budget, even as client numbers grow.
By Anna Lackinger, Andrea Morichetta, Pantelis A. Frangoudis, Schahram Dustdar
arXiv:2608. 20686v1 Announce Type: new Abstract: Many scientific discovery problems require searching combinatorial hypothesis spaces under complex domain constraints.
By Piyush Jha, Jake Rudolph, Victoria Knapp-P\'erez, Max Fieg, Aishik Ghosh, Vijay Ganesh
arXiv:2608.20566v1 Announce Type: new
Abstract: AI agents extend large language models from single prompt-response interactions to long-running, goaldirected workflows that issue many model calls, in...
By Leyi Yan, Shuangning Li, Sihang Liu
arXiv:2608.01347v4 Announce Type: replace
Abstract: Coding-agent efficiency cannot be characterized by token count or model price alone. We study how end-to-end cost and task success depend jointly o...
By Sarel Weinberger, Amir Hozez
arXiv:2608.21099v1 Announce Type: cross
Abstract: Multi-modal object detection is essential for robust scene understanding in challenging conditions, including low-light and adverse environments. Rec...
By Jiekang Feng, Zhihe Fan, Yunqi Zhu, Xinjie Yao, Yueying Zhang, Yike Gao, Ranxin Li, Guanzuo Chen
Nonverbal behavior generation systems for virtual agents often take an utterance as input and generate nonverbal behaviors that emphasize or illustrate the content of the verbal channel. However, huma...
Short-drama generation has grown into a large, industrialized pipeline, and as it scales from isolated shots to the episode level, visual continuity has become a critical bottleneck. Current agent fra...
UAV vision-language navigation (UAV-VLN) is commonly evaluated as goal reaching, but inspection-oriented deployment requires the agent to stop within a valid inspection region and avoid falsely confir...
As the use of Artificial Intelligence (AI) and Large Language Models (LLMs) is becoming common in everyday applications, their ability to interpret natural language has increased significantly. An eme...
Recent vision-language models (VLMs) show strong capabilities in robotic perception and spatial reasoning, yet their ability to reason about complex mechanical assemblies remains underexplored. We int...
Agent skills, structured artifacts distilled from interaction trajectories and dynamically reused from skill banks, have become a central mechanism for enabling large language model (LLM)-based self-e...
Policy-governed agents must interpret case evidence while reliably following authorized procedures. We present STAGE, an executable-graph framework that confines model judgment to policy-scoped nodes...
Autonomous computer-use agents are increasingly applied to long-horizon tasks requiring coordinated application calls, persistent state tracking, and verifier-sensitive writes, yet they remain prone t...
World models enable agents to reason about future outcomes and learn policies from their knowledge of state transition, but existing approaches primarily focus on reconstructing future observations or...
Explainable AI (XAI) research has produced a plethora of explanation techniques, yet user studies repeatedly show that available explanations are not effective in practice. We argue that, given the si...
The article discusses transforming a demo LangGraph AI agent into a fully functional backend capable of handling real booking data. It outlines the steps and considerations involved in building a robust system that supports live data processing and integration. The focus is on practical implementation details rather than theoretical concepts.
By Soner Yıldırım
The article discusses the essential skill of effectively instructing coding agents and verifying their changes. It highlights that while line‑by‑line code review is one method, it is not the most efficient way to validate software changes. The focus is on confidently guiding agents and confirming correct implementation without exhaustive inspection.