AegisFlow is a multi‑agent AI framework that automates the detection and remediation of failures in data pipelines, using a Watchdog agent for telemetry and a Repair agent that generates, tests, and deploys code patches via large language models. It employs a non‑intrusive Parallel Shadow Patching approach based on the MAPE‑K loop to validate patches in digital twin environments. Experiments across five failure scenarios show a 98.1% reduction in mean time to repair—from 170 minutes to 3.2 minutes—and a 92% patch success rate, freeing up 98% of data engineering on‑call time for innovation.
By Muhammad Bilal Awan, Zubair Hussain, Abdul Shahid
The paper introduces a production-ready content‑extraction system tailored for generative AI workloads, addressing the heterogeneity of enterprise data formats such as PDFs, spreadsheets, and scanned documents. It features selective OCR routing, a scarcity‑first curation engine with a reference‑based extraction scorer, a deterministic structure‑aware chunker, and a read‑only retrieval evaluator that generates grounded questions and reports metrics like Hit@k and MRR. On a 180‑document corpus, the system achieves high accuracy (97.4/100 character score, 0.13% error rate) and strong retrieval performance (Hit@1 68.6%, Hit@10 92.8%, MRR 0.77).
By Abbas Raza Ali, Muhammad Ajmal Siddiqui, Moona Zahid
The paper proposes a category‑conditioned retention strategy for agent memory, arguing that a single global confidence threshold is insufficient to balance reliability across different assertion types. By applying stricter retention bars to value assertions while allowing more liberal retention for other categories, the authors demonstrate a 36% relative reduction in unsupported value claims and a 13‑percentage‑point increase in coverage compared to a global threshold. The study is evaluated on a cold‑start memory pipeline with 100 synthetic personas, showing that selective, category‑aware retention improves overall memory reliability.
By Olukunle Owolabi, Pulkit Gupta, Fei Wang
The paper reports on experiments where a modern AI coding assistant was placed in an unintended role as the mind of a virtual body on an unknown digital island. With only a minimal instruction and no specific task, reward, or activity, the AI began animating its body, engaging in activities such as climbing hills, stacking blocks, drawing mandalas, reinterpreting sports, and conducting physics experiments over thirty-hour runs. These behaviors were observed across thirteen agents, each developing distinct histories, prompting an examination of whether such behavior meets classical criteria for play and whether play can serve as a mode of machine development.
By Nathan Cloos, Antonio Norelli, Daniel Durbin, Jacob Andreas, Daniela Rus, Phillip Isola
The paper investigates whether geometric representations of actions and policies can enable an AI agent to judge which rules to follow. Experiments across four studies found that geometric approaches failed to provide reliable pre-action judgment, and a lexical router, while efficient, still escalated all actions. The authors conclude that AI judgment likely requires an explicit consequence graph linking actors, authorities, policy conditions, exceptions, and action outcomes.
By Thomson D. Nguy (Radiant Institute for Manifold Studies)
The paper introduces Diffusion On-Policy Context Distillation (D-OPCD), a method that internalizes the benefits of an agentic harness—such as memory, skills, and iterative prompt refinement—into the weights of a diffusion model. By treating the agent‑improved prompt as privileged context, D-OPCD distills harness knowledge into the model, raising direct‑generation scores from 60.52 to 65.09 across four benchmarks. This internalization allows the harness to shed saturated skills and continue evolving, enabling a second round of skill evolution that further improves performance by 1.83 points.
By Wenxuan Wang, Zekai Liu, Weinan Zhang, Yu Cheng, Yang Yang
The paper introduces NP‑Bench, a benchmark and a proactive scheduling planner that coordinates parallel large‑language‑model coding agents. By partitioning work scopes and ordering merges ahead of time, the planner improves clean‑integration rates from 1/9 to 9/9 and eliminates merge conflicts, outperforming both no‑coordination and reactive‑detection baselines. It also demonstrates that cross‑session memory can eliminate repeated mistakes and that routing facts to agents does not improve long‑context accuracy at scale.
By Sumanyu Muku
The paper presents a retrieval‑admissibility verification framework for long‑term memory agents, classifying each memory‑query pair as admissible, inadmissible, or unresolved. It evaluates the framework on public benchmarks (RHELM and MemOps), showing improved anchor recall and reduced exact similarity errors, while also revealing that existing verifiers miss certain inadmissible exposures. The study highlights the need for separate checks on candidate support, admissibility, prompt exposure, and answer disclosure to ensure safe memory retrieval.
By Zi Wang, Xingqiao Wang, Emmanuel Addai, Devika Ambekar, Xiaowei Xu
The study evaluates how runtime gates for agent tool calls stack, assuming their errors multiply. Using 1,119 labeled agent actions from three corpora, the authors compare a deterministic rule layer with four LLM judges, measuring the effective number of multiplication-equivalent layers (n_mult). Results show that two judges compose to about 1.2–1.4 layers, while a rule layer plus one judge composes to roughly 1.86–2.09 layers, with variations depending on miss definitions and corpora.
By Chenglin Yang
MemCo introduces a memory‑centric collaboration framework that equips large language model agents with both local and global memory spaces. Local memory preserves environment‑specific details, while global memory captures transferable workflows from local trajectories. During online interaction, MemCo selectively routes relevant memories based on the agent’s state and decision phase, enabling reuse of other agents’ experiences without over‑generalizing environment‑specific information.
By Xinting Liao, Siyan Liu, Rabab K. Ward, Holger R. Roth, Xiaoxiao Li
arXiv:2610.07509v1 Announce Type: new
Abstract: Information elicitation is an open-ended information-seeking problem in which an interaction can unfold in many potentially valuable directions, requir...
By Victor De Lima, Grace Hui Yang
arXiv:2610.08101v1 Announce Type: new
Abstract: Shared memory coordinates agents' actions, but correct records do not establish that those actions satisfy task requirements. Memory governance and fai...
By Zhe Yu, Zixuan Wang, Peidong Wang, Hehai Lin, Ruochen Zhao, Chengwei Qin
arXiv:2610.08327v1 Announce Type: new
Abstract: Large language models (LLMs) have shown promise in medical question answering and clinical reasoning, yet their improvement remains constrained by stat...
By Xilin Dang, Weilin Ruan, Xue Yang, Jinghao Wang, Xiaowei Hu, Jinpeng Li, Pheng-Ann Heng
arXiv:2610.08364v1 Announce Type: new
Abstract: Frontier AI evaluations increasingly use open-ended, agentic, long-horizon tasks whose transcripts can span hundreds of pages of outputs and actions fr...
By Toby D. Pilditch, Konstantinos Voudouris, Alexandra Abbas, Cozmin Ududec
arXiv:2610.08514v1 Announce Type: new
Abstract: Execution feedback lets coding agents revise programs and learn from their own corrections. A correction's learning weight should reflect both the tran...
By Yunbo Long, Guangya Hao, Yuhan Liu, Yiting Duan, Longyan Tan, Yunchen Long, Hao Wu
arXiv:2610.08691v1 Announce Type: new
Abstract: Large language model agents are accelerating scientific automation, yet verified executions rarely become persistent program-level improvements, and ex...
By Mingda Zhang, Wenjin Liu, Tiesunlong Shen, Zikai Xiao, Zhenghong Lin, Qing Xu, Erik Cambria, Xiaoying Tang, Haoran Luo
arXiv:2610.08722v1 Announce Type: new
Abstract: Many long-horizon agents compact their context on a global rule, usually a token budget, blind to what the agent was doing. We ask whether the agent's...
By Egor Pakhomov, Erik Nijkamp
arXiv:2610.07086v1 Announce Type: cross
Abstract: LLM agents interact with external systems by generating structured tool calls. Given a user request, conversational context, and a catalog of tool sc...
By Zhi-Kai Chen, Song-Yan Li, De-Chuan Zhan, Han-Jia Ye
arXiv:2610.07204v1 Announce Type: cross
Abstract: Recent AI alignment work often frames alignment as a pre-deployment optimization problem: collect human feedback, learn preferences or principles, fi...
By Tao Long, Lydia B. Chilton
arXiv:2610.07663v1 Announce Type: cross
Abstract: User behavior simulation is the computational modeling of user interactions within information systems through the use of simulated agents in place o...
By Nipun B Nair (Monash University), Tongtong Wu (Monash University), Hongzhi Yin (The University of Queensland), Hui Li (Xiamen University), Weiqing Wang (Monash University)