Agentick is a unified benchmark for sequential decision‑making agents that evaluates RL, LLM, VLM, hybrid, and human agents on 37 procedurally generated tasks across six capability categories, four difficulty levels, and five observation modalities via a single Gymnasium‑compatible interface. It includes a Coding API, oracle reference policies, pre‑built SFT datasets, a composable agent harness, and a live leaderboard. An evaluation of 27 configurations and over 90,000 episodes shows no single approach dominates, with GPT‑5 mini leading overall, PPO excelling in planning and multi‑agent tasks, and the reasoning harness boosting LLM performance by 3‑10×, while ASCII observations outperform natural language.
By Roger Creus Castanyer, Pablo Samuel Castro, Glen Berseth
arXiv:2609.01045v1 Announce Type: new
Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities as powerful components in agentic systems, enabling sophisticated reasoning and...
By Enci Zhang, Haofeng Wang, Yuesheng Zhu, Xiaole Cui, Guibo Luo
arXiv:2608. 10504v1 Announce Type: new Abstract: As coding agents increasingly handle implementation, the central challenge shifts from building individual agents to building an infrastructure that systematically improves them.
By Jung Hwan Lee, Kyu Ho Lee, Gwang Hoon Yoo
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
arXiv:2606. 07603v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong reasoning capabilities, yet most LLM-based agents are statically deployed and unable to improve through task interactions.
By Bowen Ren, Heyan Huang, Yinghao Li, Yang Gao
arXiv:2510. 15416v2 Announce Type: replace Abstract: We investigate a framework in which LoRA adapters are treated as callable tools that a base language model can dynamically select and invoke.
By Pavan C Shekar, Aswanth Krishnan
arXiv:2602.03053v2 Announce Type: replace
Abstract: Multi-Agent Systems (MAS) built on Large Language Models (LLMs) often exhibit high variance in their reasoning trajectories. Process verification,...
By Vishal Venkataramani, Haizhou Shi, Zixuan Ke, Austin Xu, Xiaoxiao He, Yingbo Zhou, Semih Yavuz, Hao Wang, Shafiq Joty
The paper argues that the architecture of multi‑agent large language model (LLM) frameworks, rather than just the intelligence of the underlying models, largely determines system performance. It introduces a taxonomy of architectural dimensions—such as orchestration, memory, planning interfaces, specialization, and communication topology—and presents MAFBench, a unified evaluation suite. An empirical study across nine frameworks, keeping the LLM constant, reveals six design principles and shows that choices like orchestration and communication topology can dramatically affect latency, accuracy, and coordination success.
By Abdelghny Orogat, Ana Rostam, Essam Mansour
arXiv:2607. 25369v1 Announce Type: new Abstract: Agentic systems have rapidly advanced in their ability to interact with real-world environments, leverage external tools, and provide services for users.
By Jiaqi Zhang, Tong Chen, Junliang Yu, Quoc Viet Hung Nguyen, Hongzhi Yin
arXiv:2608. 05791v1 Announce Type: cross Abstract: Large language model (LLM)-driven multi-agent systems typically require multiple model invocations and complex coordination during inference, and their execution strategies directly affect system accuracy, latency, and computational cost.
By Zihan Xu, Haolin Tian, Hai Jiang
Large Language Models (LLMs) have driven rapid progress in autonomous agents, yet standard evaluations remain confined to static task solving. An emerging frontier is harness evolution---the agent's capacity to autonomously optimize its own operating harness.
Unified-MAS is a two-stage framework that decouples node implementation from orchestration in Automatic Multi-Agent Systems. It first searches external knowledge to synthesize domain‑specific node blueprints, then uses a perplexity‑guided reward to optimize bottleneck nodes. Experiments across four specialized domains show that adding Unified-MAS to existing baselines improves performance‑cost trade‑offs by up to 14.2% while lowering costs.
By Hehai Lin, Yu Yan, Zixuan Wang, Bo Xu, Sudong Wang, Weiquan Huang, Ruochen Zhao, Minzhi Li, Chengwei Qin