The paper introduces Recuris, a recursive Experiential‑Working Memory architecture that lets long‑horizon agents track task progress and select skills based on current needs rather than full history. By coupling working memory with experiential memory, execution becomes structured evidence that localizes failures to specific memory components, enabling a bounded recursive memory‑evolution loop. Across four benchmarks and ten models, Recuris improves task success in 35 of 37 model‑benchmark pairs, raising state‑of‑the‑art performance on tau‑bench and SkillFlow and reducing common long‑horizon failures by up to 80%.
By Zhaochen Yu, Yingcheng Wu, Zhenfei Yin, Kaiyuan Chen, Zhe Zhao, Mengdi Wang, Shuicheng Yan, Ling Yang
arXiv:2608.24169v1 Announce Type: new
Abstract: 3D geometry editing is a critical yet labor-intensive part of the graphics pipeline, requiring artists to translate creative intent into precise operat...
By Bo Pang, Jiaqi Pan, Xiaocheng Zhang, Jiacheng Xu, Guoping Wang, Peng-Shuai Wang
The paper investigates the cost–quality trade-offs involved when coding agents switch between low‑cost, low‑capability (LC) and high‑cost, high‑capability (HC) language models during long‑running tasks. By experimenting with different handoff directions, timings, and interfaces—full‑trajectory transfer, compaction, and trajectory removal—the authors find that full‑trajectory escalation recovers less than half of the LC‑to‑HC quality gap while adding significant cost, a penalty they call the handoff tax. Conversely, downshifting from HC to LC yields a more favorable cost‑quality balance, and the optimal interface depends on the direction of the handoff.
whyItMatters":"The study quantifies how model handoffs impact both performance and expense, offering guidance for designing more efficient coding agents that balance cost and quality."
By Roy Ganz, Mor Shpigel Nacson, Adi Kalyanpur, Ron Litman
AgentWorld is a simulation framework that evaluates agentic information retrieval by incorporating diverse user personalities based on the Big Five (OCEAN) traits, stateful tool-use environments, and a pass$^k$ consistency metric with structured fault classification and partial-credit scoring. It includes a risk analyzer that uses Monte‑Carlo rollouts and advanced scoring methods to quantify trajectory brittleness and attack attribution. Experiments with conversational analytics, customer‑support agents, and adversarial stress‑testing demonstrate that personality variation reveals failure modes hidden by uniform testing, such as cross‑domain leakage, contextual drift, and significant quality gaps across personas.
By Gunja Agarwal, Arup Kumar Das, Arun Menon, Jitesh Chandra Mishra, Vignesh Divakaran
The paper introduces AnTrap, a benchmark that injects dynamic perturbations into Android GUI agent execution to evaluate robustness against runtime anomalies. It presents a taxonomy of anomalies across four layers—State, Thinking, Action, and Round—with ten subcategories, and a pipeline that maintains task solvability while adding realistic adversarial conditions. Experiments on 16 leading GUI models show universal vulnerability, and reinforcement learning can mitigate some traps but not deep contextual ones like state deadlock.
By Guo Gan, Yilun Zhao, Cong Chen, Jinbiao Wei, Tingyu Song, Zheyuan Yang, Lin Fu, Hong Zhou
Paritok-4B is a 4‑billion‑parameter LoRA compressor designed for coding agents, which extracts and retains key spans of code rather than paraphrasing them. It is intent‑conditioned, selecting lines that are most relevant to the agent’s current task, and achieves high fidelity with 96% of identifiers, paths, and numbers preserved. Trained on 67,074 real OpenHands trajectories and fine‑tuned on Qwen3‑4B, it compresses agent context to about 25.7% of its original size while keeping 86.5% of the uncompressed solve quality across 300 SWE‑bench Lite instances.
By Jiayu Shi, Luzhuo Chen
The paper introduces Adaptive Influence Graphs (AIGs), a two‑stage framework that first converts a failed trace into a structured graph and then navigates it to pinpoint the critical error in multi‑agent large language model systems. Experiments across multiple models demonstrate that richer trace representations and adaptive graph construction improve failure attribution, with AIGs achieving state‑of‑the‑art results on the Who&When benchmark. The study shows that both the diagnosing model and the way traces are represented and explored are crucial for accurate failure attribution.
By Yarden Bakish, Amir Dudai, Roy Ganz, Oren Nuriel, Elad Ben Avraham, Mor Shpigel Nacson, Ron Litman
MetaRAG introduces a belief-action aligned policy optimization framework for agentic retrieval-augmented generation (RAG). It incorporates Verify-first Action Generation and Internal Belief Probing to assess whether the current evidence is sufficient before taking an action, and uses a consistency reward gated by answer correctness to guide training. Experiments on seven public QA benchmarks demonstrate that MetaRAG improves the accuracy-efficiency trade-off over existing RL-based agentic RAG baselines, with benefits that transfer across research settings, optimizers, and model backbones.
By Qiuyi Qi, Tian Liang, Jiamu Wang, Jinjian Zhang, Wei Zhou, Pengcheng Zhu, Linjian Mo, Ming Kong, Jie Liu, Qiang Zhu
The paper introduces ICA, an evidence‑centric framework that represents information from web‑tool interactions as stable, rendered snapshots, enabling comparison across trajectories. It proposes Information‑Aware Credit Assignment, a post‑hoc reward propagation technique that estimates turn‑level utility from rollout success and assigns dense rewards to steps that provide high‑utility information. When combined with GSPO, ICA consistently improves performance on several web‑search benchmarks such as BrowseComp, GAIA, Xbench‑DS, and Seal‑0.
By Cong Pang, Xuyu Feng, Yujie Yi, Jiaqi Su, Zixuan Chen, Jiawei Hong, Tiankuo Yao, Nang Yuan, Jiapeng Luo, Lewei Lu, Xin Lou
arXiv:2509.15959v2 Announce Type: replace-cross
Abstract: Autonomous navigation in maritime domains is accelerating alongside advances in artificial intelligence, sensing, and connectivity. Opaque de...
By Zhuoyue Zhang, Haitong Xu, Carlos Guedes Soares
arXiv:2510.21536v5 Announce Type: replace-cross
Abstract: Free-space segmentation is essential for autonomous robots to identify drivable regions and navigate safely across indoor, outdoor, and road-...
By Narendhiran Vijayakumar
arXiv:2505.11239v4 Announce Type: replace
Abstract: Understanding human mobility through Point-of-Interest (POI) trajectory modeling is increasingly important for applications such as urban planning,...
By Wilson Wongso, Hao Xue, Flora D. Salim
arXiv:2608.24743v1 Announce Type: new
Abstract: Existing linear program (LP) and semidefinite program (SDP) relaxations for rectified linear unit (ReLU) neural network (NN) verification yield overly-...
By Hanna Jiamei Zhang, Alan Papalia, Michael Everett, David M. Rosen
arXiv:2603.00188v2 Announce Type: replace-cross
Abstract: Training-free KV cache compression is essential for deploying vision-language GUI agents under memory and latency constraints, yet existing m...
By Bowen Zhou, Zhou Xu, Wanli Li, Jingyu Xiao, Pingan Gan, Haoqian Wang
EngiAI introduces a capability-based evaluation framework for tool-connected engineering agents, assessing workflow execution, retrieval-assisted parameter selection, HPC orchestration, and training-code authoring using execution traces and engineering artifacts. The framework was applied to four LLM backends on EngiBench Beams2D and Photonics2D, revealing that proprietary models outperform open-source ones in workflow completion and HPC orchestration, while indexed retrieval improves parameter selection. The study demonstrates that evaluating distinct skills separately provides clearer insight into failure mechanisms than end-to-end success rates alone.
By Gioele Molinari, Florian Felten, Soheyl Massoudi, Mark Fuge
The paper introduces a new framework for analyzing multimodal data—visual, auditory, and spatial—by focusing on the complexity of embodied perception and interaction in dynamic, naturalistic settings. It expands upon prior visual complexity work to categorize diverse attributes (quantitative, structural, dynamic, auditory, interactional) that together describe multimodal complexity. The authors illustrate how this model can characterize visuospatial complexity in everyday driving and suggest its use for creating and evaluating benchmark datasets that prioritize cognitive human factors.
By Vasiliki Kondyli, Jakob Suchan, Mehul Bhatt
The paper introduces AdaptRubric, a Coarse-to-Fine Rubrics Framework designed to create task‑adaptive judging criteria for GUI reward modeling. It first retrieves a category‑level coarse rubric by mapping instructions to a GUI task family, then generates an instance‑level fine rubric that captures specific values, scopes, and constraints from the instruction. Experiments show that AdaptRubric outperforms existing reward agents, improving F1 by 3.6 points and achieving a 4.23‑point task‑success gain under a matched image budget.
By Tao Xiong, Xavier Hu, Wenkai Wang, Qinzhuo Wu, Changqiao Wu, Pengzhi Gao, Wei Liu, Jian Luan, Shengyu Zhang
TRACE is a transition‑aware residual control framework designed to improve multi‑objective materials discovery with large language model agents. It records each local refinement as a parent‑edit‑child transition, aggregates evidence to estimate reusable edit effects, and ranks future edits by their predicted ability to reduce remaining constraint violations while protecting already satisfied objectives. In a controlled comparison, TRACE outperforms the state‑of‑the‑art LLEMA baseline, raising the macro‑average hit rate from 18.13% to 25.96%.
By Kang Zhou, Yujia Tong, Yong Tao, Jingling Yuan
The paper introduces TruthMarketTwin, a simulation framework that uses agent-based modeling to study large language model (LLM) agents in e‑commerce markets characterized by asymmetric information. It models bilateral trade where sellers and buyers make strategic decisions about listings, purchases, ratings, and recourse to maximize profit and utility. The study finds that LLM agents can autonomously exploit weaknesses in reputation‑based governance, but that warrant enforcement can reduce deception and alter strategic behavior.
By Shijun Lei, Quang Nguyen, Swapneel S Mehta, Zeping Li, Huichuan Fu, Xiaolong Zheng, Siki Chen, Yunji Liang, Philip Torr, Zhenfei Yin
The paper introduces a method to transform entire trace corpora of LLM-based agents into compact finite-state machines (FSMs) that capture shared behavioral structure. These FSMs, comprising 7–43 states, achieve near-perfect replay of held‑out data and enable accurate next‑step prediction and failure detection across twelve public datasets. The approach offers a model‑agnostic structural tool for safety auditing and runtime monitoring of agent behavior.
By Seonglae Cho, Franklin Cardenoso Fernandez, Umar Mohammed, Zekun Wu, Kleyton Da Costa, Ilham Wicaksono, Adriano Koshiyama