Recent arXiv work surfaced by a deterministic topical search for autonomous reasoning, cognitive architectures, agentic AI and adjacent systems research.
arXiv · 2026-10-09 · relevance score 4
A Local Agentic AI Framework to Generate Edge Case Scenarios for Safety Assurance
Victoria J. Hodge, Colin Paterson, Rob Alexander
Generating edge case scenarios is crucial for training, testing and safety assuring autonomous systems. This identifies hazardous failures to increase system reliability and robustness, ensures the system can still function safely on the boundaries of its operational design domain and learns the expected system behaviour for these edge cases. The rapid advancement in the…
Read on arXiv ↗
arXiv · 2026-10-09 · relevance score 4
The value of information and the emergence of communication in evolved e-puck robots
Fernando Montes-Gonzalez
We study when communication emerges between autonomous agents and what role an innate action selection architecture plays. Two e-puck robots, reconstructed in PyBullet from their Webots model and validated against it, must find a feeding zone that can only be detected when a robot passes over it. Each robot can emit a one-bit signal whose direction is detected by the receiver.…
Read on arXiv ↗
arXiv · 2026-10-08 · relevance score 8
Unlocking the Regulatory Genome by ARGUS: An Evidence-Constrained Agentic Framework for Interpreting Single Nucleotide Variants
Pratik Dutta, Matthew B. Obusan, Max Chao, Rekha Sathian, Nimisha Papineni, Ramana V. Davuluri
Over 90% of disease-associated variants from genome-wide association studies fall in noncoding regulatory regions, yet their functional interpretation remains a central open problem in genomic medicine. Large language models prompted to interpret such variants routinely hallucinate transcription factor (TF) binding changes, fabricate experimental support, and assign biological…
Read on arXiv ↗
arXiv · 2026-10-08 · relevance score 4
Gamma: Grounded Multi-Agent Memory with Mechanical Audit for Memory-Intensive Manipulation
Yudong Liu, Yueqian Lin, Zijia Tang, Yuxi Zheng, Yuan Li, Shuai Zhang, Yi Li, Taotao Jing, Shuangjun Liu, Dashan Gao, Ning Bi, Jingwei Sun, Yiran Chen, Hai Helen Li
Pretrained vision-language-action (VLA) policies fail on memory tasks, behaviour that depends on events observed long before the current frame, because their training data is overwhelmingly Markov and mapping episodic memory directly to action chunks is hard. Yet the same policy, finetuned once to follow a privileged oracle's grounded-subgoal text, nearly solves these tasks:…
Read on arXiv ↗
arXiv · 2026-10-08 · relevance score 4
Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational Agents
Yichen Liu, Chunfeng Yuan, Haowei Liu, Wenjuan Li, Zefeng Lin, Bing Li, Xu Chen, Weiming Hu
For persistent and personalized conversational agents, memory systems can enable them to remember, update, and reason over long histories by storing past interactions and retrieving relevant information. Existing memory systems typically follow two paradigms: flat-structured memory and graph-based memory. The former is lightweight but leaves event relations and state updates…
Read on arXiv ↗
arXiv · 2026-10-08 · relevance score 4
GROB: A Multi-Agent Architecture for Public-Trace Investigation of Candidate Agentic Activity
Chiara Bonfanti, Cataldo Basile
We present GROB, a multi-agent architecture for investigating candidate autonomous-agent activity through public Internet traces when privileged telemetry is unavailable. The system performs controlled, read-only collection of public traces and preserves selected observations for later resolution. In a frozen September 2026 corpus, several collected traces became more…
Read on arXiv ↗
arXiv · 2026-10-07 · relevance score 10
NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime
Gengze Zhou, Yicong Hong, Jiazhao Zhang, Xunyi Zhao, Jian Zhou, Zixing Lei, Zun Wang, Chongyang Zhao, Xionghui Chen, Stephen Gould, Anton van den Hengel, Qi Wu
Language models trained with long-horizon agentic reinforcement learning can generalize knowledge through reasoning, express precise actions, and pursue goals over many steps, raising the ceiling on what an embodied agent can understand and decide. Physical interaction, however, remains the domain of action policies, which provide dense, low-latency control. We present…
Read on arXiv ↗
arXiv · 2026-10-07 · relevance score 9
Verification and Self-Improvement in Agentic AI: Foundations and Limits
Chien-Ping Lu
Agentic AI systems can improve by searching longer, receiving additional support, or modifying how they propose and verify outputs. A performance score does not distinguish these mechanisms. We compare these changes through bounded verification with hidden terminal randomness. A stage specifies admissible transcripts, polynomial bounds, an alternating verification protocol,…
Read on arXiv ↗
arXiv · 2026-10-07 · relevance score 8
iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains
Vincenzo Guarino, Emanuele Musumeci, Vincenzo Suriani, Daniele Nardi
Agentic AI based on Large Language Model generalization capabilities offers a wide range of potential applications, including planning for embodied tasks. For example, embodied agents based on Foundation models can generate plausible plans in autonomous robotics scenarios. Due to limited context windows or hallucinatory phenomena in the next-token prediction formulation,…
Read on arXiv ↗
arXiv · 2026-10-07 · relevance score 8
Learning Situation-Conditioned Thinking Policies for Long-Term LLM Agents
Hong Su
Long-running autonomous agents must reuse accumulated reasoning experience without allowing explicit historical memory and LLM context to grow indefinitely. However, existing memory mechanisms mainly retrieve, summarize, or compress past content and do not directly learn when particular kinds of thinking should be activated or discover new thinking knowledge from temporally…
Read on arXiv ↗
arXiv · 2026-10-07 · relevance score 6
RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip Design
Awani Khodkumbhe, Yunfei Feng, Raj Rangarajan, Kevin Wang, Kamal Sahota
Analog/RF circuits remain the critical interface between digital computation and the physical world, and emerging standards from Wi-Fi 7 to 6G place stringent demands on them, yet analog/RF design remains one of the most labor-intensive steps in chip development. We present RFChipAgent, a first-of-its-kind multi-agent flow of large language model (LLM) agents for end-to-end…
Read on arXiv ↗
arXiv · 2026-10-07 · relevance score 6
When My Skill Becomes Agent Skill: How Knowledge Workers Share Their Expertise with AI Systems
Tianqi Song, Zicheng Zhu, Hancheng Cao, Yi-Chieh Lee
Organizations have long sought to make workers' expertise reusable by others. Agentic AI changes the nature of such reuse by enabling AI systems to act on workers' knowledge with limited human involvement. This raises the question of how this shift shapes workers' willingness to share their expertise. We conducted an experiment with knowledge workers who created materials…
Read on arXiv ↗