AI Agents & Automation

The setup Last week I built MarketNow, an open marketplace for MCP (Model Context...

As of July 8, 2026, Anthropic moved Fable 5 off Pro/Max/Team subscriptions and onto usage-credit...

Winning a Customer Is Hard. Winning Them Back Is Even Harder. Continue reading on Medium »

A publishing guardrail only works when the AI agent cannot bypass it. Move safety from a script it should call to a wall it cannot cross.

The robot apocalypse, as far as I can tell, is a Figure unit putting one piece of sheet metal in one slot at a BMW plant, over and over… Continue reading on Med

The robot apocalypse, as far as I can tell, is a Figure unit putting one piece of sheet metal in one slot at a BMW plant, over and over… Continue reading on Med

arXiv:2607.02542v1 Announce Type: new Abstract: General-purpose embodied agents must understand multimodal instructions, anticipate how their environment will e

arXiv:2607.02771v1 Announce Type: new Abstract: Leadership computing facilities steward large-scale scientific datasets that routinely require substantial trans

arXiv:2607.02807v1 Announce Type: new Abstract: Long-running coding agents such as autoresearch can persistently discover optimizations for open-ended problems.

arXiv:2607.02846v1 Announce Type: new Abstract: Large language model (LLM) agents can improve through accumulated experience, but free-form textual memories bec

arXiv:2607.02931v1 Announce Type: new Abstract: AI tools are accelerating scientific publication while the systems that review it struggle to keep up, and indep

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

arXiv:2607.03015v1 Announce Type: new Abstract: Forecasting future events has attracted growing attention as a testbed for general-purpose AI. A natural way to

arXiv:2607.03283v1 Announce Type: new Abstract: Embodied intelligence systems require not only end-to-end policy models, but also reusable functional modules th

arXiv:2607.03386v1 Announce Type: new Abstract: Agentic AI systems are increasingly used to edit, refine, and repair decision policies, but evaluating these edi

arXiv:2607.03550v1 Announce Type: new Abstract: Human reasoning often operates through qualitative concepts expressed by linguistic labels such as high, low, ex

arXiv:2607.03702v1 Announce Type: new Abstract: Large language model (LLM) agents have shown strong decision-making capabilities in long-horizon interactive tas

arXiv:2607.03703v1 Announce Type: new Abstract: Reinforcement Learning (RL) has emerged as a powerful paradigm for adaptive traffic signal control. However, in

arXiv:2607.03787v1 Announce Type: new Abstract: Accurately modeling biomolecular interactions is a central bottleneck in biology and therapeutic discovery. Here

arXiv:2607.04089v1 Announce Type: new Abstract: Lifelong agents need more than larger context windows and better retrieval. They need memories that can persist,

arXiv:2607.04096v1 Announce Type: new Abstract: Current agentic workflows usually involve decomposing user requests into sequences of tool calls with correctly

arXiv:2607.04219v1 Announce Type: new Abstract: The integration of AI into Internet of Things (AIoT) systems has gradually transformed them from passive data co

arXiv:2607.04240v1 Announce Type: new Abstract: The transition of Large Language Models (LLMs) from passive generators to autonomous agents has introduced signi

arXiv:2607.04242v1 Announce Type: new Abstract: Group-based reinforcement learning (RL) has become an effective paradigm for improving large language model agen

arXiv:2607.04292v1 Announce Type: new Abstract: Ransomware has evolved into a complex, adaptive, and fast-moving adversary category in which static signatures a

arXiv:2607.04334v1 Announce Type: new Abstract: Multimodal GUI agents read an interface through two redundant channels: the rendered pixels of a screenshot and

arXiv:2607.04336v1 Announce Type: new Abstract: Modern video games are becoming more complex day by day. Most of these modern games are multiplayer first-person

arXiv:2607.04419v1 Announce Type: new Abstract: Most agent evaluations collapse a multi-step trace into a final answer, a success flag, or a trajectory-level sc

arXiv:2607.04508v1 Announce Type: new Abstract: Agentic AI-for-Science can automate ideation, planning, and analysis, but final validation still depends on real

arXiv:2607.04590v1 Announce Type: new Abstract: Pairwise human comparisons are a primary interface through which modern AI systems learn human preferences. RLHF

arXiv:2607.04613v1 Announce Type: new Abstract: Autonomous agents are moving from sandboxed text generators to operators of code, data, and physical infrastruct

arXiv:2607.04710v1 Announce Type: new Abstract: Inducing cooperation among distributed agents is still a difficult problem in the field of multi-agent reinforce

arXiv:2607.04718v1 Announce Type: new Abstract: Deep research agents decompose open-ended queries into subtasks, retrieve web evidence over multiple rounds, and

arXiv:2607.04758v1 Announce Type: new Abstract: Physical design quality-of-results~(QoR) optimization is hard and expensive. Choices made at one stage can help

arXiv:2607.05177v1 Announce Type: new Abstract: Workforce scheduling is an NP-hard combinatorial optimization problem requiring simultaneous satisfaction of lab

arXiv:2607.05185v1 Announce Type: new Abstract: Compositional generalization, the ability to understand and produce novel combinations of known components, rema

arXiv:2607.05202v1 Announce Type: new Abstract: Agent self-evolution in long-horizon LLM systems is largely procedural: useful experience is not merely stored i

arXiv:2607.05346v1 Announce Type: new Abstract: We propose OptiAgent, a multi-agent framework that, given a natural language description of an Operations Resear

arXiv:2607.05363v1 Announce Type: new Abstract: Personal agents are becoming persistent user-owned intermediaries: they remember preferences, filter platform-me

arXiv:2607.02520v1 Announce Type: cross Abstract: Automated research agents increasingly generate code, retrieve literature, and draft scientific artifacts, but

arXiv:2607.02544v1 Announce Type: cross Abstract: DiLoCo-style training reduces communication by letting learner islands train locally before occasional outer s

arXiv:2607.02567v1 Announce Type: cross Abstract: Radio frequency fingerprint identification (RFFI) provides a physical-layer credential for Internet of Things

arXiv:2607.02599v1 Announce Type: cross Abstract: Tool-using LLM agents are usually evaluated by final-answer correctness or LLM judges. Neither captures how an

arXiv:2607.02615v1 Announce Type: cross Abstract: Generating structured artifacts with Large Language Models - e.g. database queries, threat framework mappings,

arXiv:2607.02622v1 Announce Type: cross Abstract: Multiplex CRISPR-Cas9 gene editing requires selecting one guide RNA per target gene subject to cross-gene inte

arXiv:2607.02640v1 Announce Type: cross Abstract: Real-time interaction models -- Moshi, MiniCPM-o, Qwen-Omni -- turn serving into a periodic real-time task: on

arXiv:2607.02724v1 Announce Type: cross Abstract: Reliable internet access is essential for modern education, yet millions of school-aged children especially in

arXiv:2607.02814v1 Announce Type: cross Abstract: Personal agents will increasingly negotiate on behalf of users: splitting costs with other personal agents, ap