The paper introduces Pivot-and-Station Multi-Agent Path Finding (PS‑MAPF), a variant of MAPF where a subset of agents must visit interchangeable pivots before all agents occupy anonymous stations. It provides a full solvability characterization: every instance on a 2‑edge‑connected graph is solvable, and for arbitrary connected graphs a structural effective‑distance measure relative to unoccupied vertices gives a necessary and sufficient condition. The authors prove that minimizing station‑makespan or station‑flowtime is NP‑hard even with a single pivot, and present three algorithms—a complete baseline, a SAT‑based optimal solver, and Pivot‑Prioritized Planning (PPP), which solves 74‑89% of benchmark instances with significantly lower makespan and flowtime than the baseline.
By Andrea Di Nezza, Mihir Patel, Fabio Fagnani, Sara Bernardini
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
The paper introduces Evidence-Carrying Termination (ECT), a method that allows tool‑using large language model agents to declare a task complete only when a typed certificate links every required answer claim to valid, in‑scope trace evidence and a deterministic replay confirms the claimed value. In controlled experiments across 48 synthetic tasks and 576 trajectories, ECT eliminated unsafe completions and premature unsupported terminations, outperforming existing termination critics and controllers while maintaining comparable supported completion rates.
By Jason Liu
SAGE is a multi‑agent framework that transforms Chinese ancient document understanding from direct answer generation into evidence‑grounded inference. It orchestrates specialized agents for planning, evidence acquisition, claim verification, and bounded replanning within a shared‑state runtime, enabling evidence seeking, answer revision, and abstention when grounding is lacking. Experiments on the AncientDoc benchmark show that SAGE outperforms direct‑answering baselines across three LVLM backbones, and even a 9B‑parameter Qwen3.5 model surpasses larger monolithic LVLMs, underscoring the value of structured, evidence‑grounded inference over mere model scaling.
By Yuchuan Wu, Xuan Luo, Yinglian Zhu, Meng Fang, Xiangyang Xue, Bin Li
Design-to-Plan is a large language model–based multi‑agent framework that automates end‑to‑end manufacturing process planning from 3D CAD models and 2D engineering drawings. The system uses an orchestrator to coordinate specialized agents for feature recognition, drawing analysis, context fusion, knowledge retrieval, process sequencing, tool selection, and report generation, integrating deterministic modules with LLM reasoning. Evaluation on 300 benchmark cases shows high success rates, strong tool selection accuracy, effective conflict detection, and reduced token usage, demonstrating the framework’s ability to produce consistent, traceable design‑to‑plan outputs.
By Muhammad Tayyab Khan, Lequn Chen, Wenhe Feng, Seung Ki Moon
WebMCP-Phalanx introduces a dual‑layer runtime for browser‑integrated LLM agents that enforces trust boundaries on web‑exposed tools. The first layer uses cryptographic capability credentials to bind tools to their registering principals and propagate provenance labels, while the second layer separates semantic inspection from privileged tool use via a Quarantine Agent that validates tool metadata before a Privileged Agent can execute it. Empirical results show the approach eliminates revocation and overwrite attacks, blocks most prompt‑injection attempts, and maintains task utility comparable to a no‑attack baseline.
By Lin-Fa Lee, YI-YU Chang, Kuo-Hui Yeh
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 documents the migration of a live conversational recommendation system from a gradient‑boosted multiclass model to a pairwise‑binary deep recommender. It explains how reformulating the task, using negative sampling, noise injection, and attention pooling over transcript chunks enabled the new model to handle dynamic, multimodal data and long conversation context. The authors compare several architectures and loss functions, showing that the deep recommender matches or surpasses the CatBoost baseline, especially in later conversational stages.
By Sonia Sharma, Jeyendran Balakrishnan, Shreya Rajpal, Swapnil Parekh, Nagaraj Janardhana, Andrew Mattarella-Micke
STRIVE is a new framework for longitudinal radiology report generation that separates clinical reasoning into distinct Diagnosis, Attribute, and Temporal Change agents, each producing explicit evidence. The Temporal Change agent is refined with a Progression-Aware GRPO reward that differentiates direction-preserving errors from reversals. Verification occurs twice: a Consistency Gate aligns agent outputs before report generation, and a Validation Agent ensures the final report is supported by the aggregated evidence. On the Longitudinal-MIMIC dataset, STRIVE achieves superior clinical efficacy and more than doubles Longitudinal Change Concordance compared to the strongest baseline.
By Junyeong Maeng, Eunsong Kang, Heung-Il Suk
arXiv:2608.24650v1 Announce Type: cross
Abstract: System-level simulation is an essential tool for exploring the rapidly expanding design space of LLM serving systems, where real deployments remain c...
By Wonung Kim, Hyunmin Choi, Minsu Kim, Jaehong Cho, Yeongwook Kim, Jongse Park
arXiv:2608.24644v1 Announce Type: cross
Abstract: This paper introduces an environment for constructing literate programs in concert with language-aware machine agents. This environment includes a gr...
By Adam T. Burke
The paper introduces a Bayesian self‑escalation strategy for hierarchical large‑language‑model agents, allowing an agent to detect during its own reasoning that it is unlikely to succeed and hand control over to a stronger model. The authors formalise this as an optimal‑stopping problem over a learned competence posterior, derive a myopic escalation threshold, and prove that the optimal policy is a time‑varying threshold without assumptions on the raw signal. They provide theoretical guarantees—including a 1/√n regret decay with n calibration trajectories—and validate the approach in simulations and a real‑model code‑generation cascade, showing that the escalation frontier outperforms post‑hoc routing at equal cost.
whyItMatters":"The study offers a principled, theoretically grounded method for agents to dynamically decide when to seek stronger models, potentially improving efficiency and reliability in hierarchical LLM systems."
By Nadeem Shaikh
The study investigates why small language model agents tend to repeat a tool call that just failed. By recording the failed call and its error message in the transcript, the authors measure a negative corrective gain—agents are more likely to repeat the failed action, with a drop of about 1.03 nats per token. The problem is traced to the harness design rather than the model’s understanding of errors, and the authors show that replacing the verbatim call with a runtime-generated description of the failure can reduce this backfiring effect by 76%.
By Esmail Gumaan
arXiv:2608.24535v1 Announce Type: new
Abstract: Data visualizations are widely used for communicating information, but they are also vulnerable to intentional manipulations that induce misleading int...
By Xiaotian Zhang, Huayuan Ye, Haiyang Zhang, Chenhui Li, Changbo Wang, Sicheng Song
arXiv:2604.06621v2 Announce Type: replace-cross
Abstract: Dr. David Blackwell was a mathematician and statistician of the first rank, whose contributions to statistical theory, game theory, and decis...
By Napoleon Paxton
ACE is a self‑correcting agentic canvas editor that operates on a hierarchical scene‑graph rather than flat document formats, enabling reliable multi‑slide presentation automation. It pairs a presentation‑specialized action space of 98 tools with CARE, a content‑aware router that reduces input tokens by about 89%, and a ground‑truth‑free instruction‑following judge that feeds natural‑language critiques back into the agent for self‑correction. In benchmarks, ACE outperforms a comparable agentic HTML pipeline on instruction following (4.23 vs. 3.81), runs 1.75× faster, costs 44% less, and is preferred by 58.7% of blind raters, with 81% favoring the self‑corrected output.
By JooYoung Jang, Taegyeong Lee, Jihyeon Park, Nojun Kwak
arXiv:2603.17170v2 Announce Type: replace-cross
Abstract: AI agents increasingly execute users' natural-language (NL) tasks by calling Web services, yet today's Web authorizes these calls through OAu...
By Reshabh K Sharma, Linxi Jiang, Shuo Chen, Zhiqiang Lin
arXiv:2608.24282v1 Announce Type: new
Abstract: Adaptive LiDAR scanning concentrates a limited sensing budget on regions of interest predicted from past object tracks, lowering data volume in autonom...
By Jiachen Gong, Yun Li, Ehsan Javanmardi, Wencan Mao, Manabu Tsukada
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
arXiv:2608.24555v1 Announce Type: cross
Abstract: Prehospital stroke assessment aims to accurately identify stroke symptoms and make rapid decisions through standardized procedures within an extremel...
By Wentao Yang, Zhenye Xu, Ruoyi Li, Musen Zhang, Yao Guo