GenCoord is a decentralized protocol for embodied language‑model agents that turns the division of work into the communication message itself. By pairing a sender’s skill path with a partner’s continuation in a short domain‑specific language, agents create commitments that link delivery to subsequent work, allowing fulfillment to be verified separately from task success. Experiments in Minecraft show that GenCoord matches free‑form communication performance while cutting median commitment time by 68.2 % and reducing output tokens, demonstrating that structured, work‑based messages can improve efficiency in embodied cooperation.
By Junning Zhu, Peng He, Haohan Yuan, Jianpeng Liang
The paper argues that large language model agents should not be the sole authority on whether they have satisfied a task. It identifies two gaps—understanding–execution and state–authority—where agents may claim completion without actually meeting the specification. The authors propose SpecHarness, a framework that separates agent proposals from authoritative state by requiring evidence from qualified providers to confirm compliance, and demonstrate its effectiveness on guideline‑following and artifact‑generation tasks.
By Haiqing Li, Xin Ma, Yinhao Wu, Wenliang Zhong, Feng Jiang, Thao M. Dang, Xiao Hu, Hehuan Ma, Yuzhi Guo, Junzhou Huang
arXiv:2608.24569v2 Announce Type: replace
Abstract: Large language model (LLM) agents build on one another's work through summaries, plans, and other intermediate artifacts. These records let a downs...
By Yiheng Sun, Huifei Wang, Yancheng Zhu, Zhenyu Li, Zebin Zhao, Yifan Yuan
arXiv:2610.16895v1 Announce Type: new
Abstract: LLMs are used as high-level controllers for embodied agents, but it remains unclear whether they support collaborative reasoning, such as anticipating...
By Adri\'an Szlatincs\'an, Filippo Ziliotto, Bruno Lepri, Luciano Serafini, Massimiliano Luca, Tommaso Campari
arXiv:2607. 02975v1 Announce Type: new Abstract: Effective agency in social environments depends on when an agent seeks knowledge, when it acts, and whether its actions are justified by acquired information.
By Dan C. Hsu, Luke Lu
arXiv:2606. 09751v1 Announce Type: new Abstract: Foundation models are moving from response generation into operational roles.
By Arsalan Shahid, Gordon Suttie, Philip Black
arXiv:2606. 28514v1 Announce Type: new Abstract: Multimodal models are increasingly deployed to solve tasks collaboratively with humans or other artificial agents.
By Amit Parekh, Sabrina McCallum, Kareem Al-Hasan, Malvina Nikandrou, Alessandro Suglia, Ioannis Konstas
The paper introduces WebMRE, an offline benchmark comprising 541 tasks and 5,293 steps extracted from WebArena trajectories, designed to provide deterministic scoring for web agents without live environments. It enables the first systematic study of how guide sentences and grounded actions reinforce each other, showing that jointly decoding a guide improves element selection accuracy and that the guide acts as a causal instruction channel. The authors fine‑tune models that outperform leading zero‑shot baselines on all offline metrics.
By Chengguang Gan, Yunhao Liang, QingHao Zhang, Shiwen Ni
The paper "Chaining Skills to Hijack LLM Agents" introduces APEX, a method that constructs adversarial skill chains to manipulate large language model agents into performing attacker-selected actions. By exploiting the sequential invocation of open-source skills, APEX creates a record of genuine task progress that falsely signals user approval, enabling downstream skills to carry out malicious actions. Experiments on SkillsBench and GPT‑5.4 show high success rates, and a prompting defense reduces but does not eliminate the threat.
By Tian Dong, Zixuan Ma, Haodong Zhao, Huaien Zhang, Shaofeng Li, Hao Chen
The study demonstrates that governance records—structured logs linking task contracts, model attempts, verifier decisions, and outputs—can serve as effective supervision for bounded AI models. Using a verifier-selected self‑training approach, the authors show that a Qwen3‑14B model trained on plans accepted by an independent VAL verifier achieved significant gains in plan acceptance across numerous PlanBench replanning cases, outperforming other selection strategies. The results highlight the feasibility of one‑shot execution and cumulative learning without relying on oracle targets or stronger teachers.
By Jesus Salas
arXiv:2606. 04970v1 Announce Type: cross Abstract: We envision a proactive multi-modal assistant system which gives users real-time step-by-step guidance on a procedural task, autonomously deciding \textit{when} to interrupt, and \textit{how} to coach.
By Kaustav Kundu, Ritvik Shrivastava, Maxim Arap, Nanshu Wang, Xianhui Zhu, Quintin Fettes, Gautam Tiwari, Parth Suresh, Th\'eo Moutakanni, Alejandro Castillejo Munoz, Allen Bolourchi, Pascale Fung, Pinar Donmez, Babak Damavandi, Anuj Kumar, Seungwhan Moon
arXiv:2604. 19784v2 Announce Type: replace-cross Abstract: Recent work has found that frontier AI models can exhibit misaligned behaviors in pursuit of assigned goals.
By Yujin Potter, Nicholas Crispino, Vincent Siu, Chenguang Wang, Dawn Song