Agentic AI

TL;DR for operators Most LLM agent failures are still discussed as if the model had a grand philosophical lapse: bad reasoning, weak planning, insufficient context, not enough “agenticness” sprinkled on top. This paper points to a less glamorous culprit: parameter filling. A tool-agent chain can fail because the model supplies the wrong field name, omits a required value, invents a value not present in the user request, misreads a tool return, or follows a type description that was wrong in the first place.1 ...

TL;DR for operators A suspicious domain appears in a DNS log. A conventional classifier either recognises it, misses it, or assigns a confidence score that someone in the SOC must interpret while pretending the queue is under control. The paper’s more interesting proposal is not “let an LLM summarise the alert”. That would be the enterprise equivalent of putting a helpful intern on a fire alarm. ...

TL;DR for operators Chain-of-thought monitoring is not “AI explaining itself.” That would be too convenient, and convenience is not usually how safety engineering works. The paper argues something narrower and more useful: when reasoning models solve hard tasks, some of their intermediate cognition may pass through human-readable language. That creates a rare oversight opportunity. A separate monitor can inspect the reasoning trace and flag signs of reward hacking, prompt-injection obedience, sabotage, manipulation, or evaluation artefacts before the final action is trusted. ...

A small property management company redesigned its human-coordination-heavy rental workflow into a stateful AI-agent-enabled operating system with structured intake, triage, exception review, contractor coordination, and owner reporting.

TL;DR for operators TinyTroupe is not another “let’s make five agents debate the product roadmap” toy. The paper’s useful move is sharper: it treats persona simulation as a different engineering problem from assistive AI.1 Assistive agents are trained to be helpful, polite, comprehensive, and often suspiciously agreeable. Human simulation needs almost the opposite: inconsistency, reluctance, taste, memory, background, class signals, cultural context, and the ability to say “no” for reasons that are not optimised for the user’s happiness. Annoying, yes. Also known as customers. ...

TL;DR for operators Static RAG is still useful. It is also no longer the whole game. The paper behind this article argues that retrieval and reasoning are converging into a more tightly coupled architecture: reasoning can improve retrieval, retrieval can improve reasoning, and agentic systems can interleave both over multiple steps.1 That sounds like a neat academic symmetry until you put it inside an enterprise workflow, where every extra retrieval call means latency, cost, permissions, ranking risk, and one more place for the machine to confidently ingest rubbish. ...

TL;DR for operators RALLY is not a chatbot with propellers. It is a hybrid control framework for UAV swarms where the LLM supplies structured semantic reasoning and the reinforcement-learning layer decides how agents should divide responsibility.1 The practical insight is the separation of labour. A drone swarm does not only need to know where to fly; it needs to agree who should lead, who should coordinate, who should follow, and when those roles should change. RALLY handles that by combining two-stage LLM consensus with RMIX, a role-value mixing network trained to assign Commander, Coordinator, and Executor roles under partial observability and limited communication. ...

TL;DR for operators Causal Influence Prompting, or CIP, is a safety method for LLM agents that asks the model to build and consult a causal influence diagram before acting. Instead of telling the agent, “be safe,” it asks the agent to represent the task as a graph: what facts matter, what choices are available, what outcomes are useful, and what outcomes are harmful. This is a better shape for the problem, because agents do not merely answer questions. They click buttons, run code, forward messages, use tools, and occasionally behave as if “sure, why not?” were a compliance framework. ...

TL;DR for operators A support agent reads a customer email. It checks a CRM record. It calls a refund API. It writes a note into long-term memory. It asks another agent to verify policy. Somewhere in that chain, a malicious instruction hides inside a message, document, issue tracker entry, retrieved snippet, schema, or tool response. The model does not need to become “evil”. It only needs to be helpful in the wrong direction. ...

A mid-sized e-commerce company evolved a generic outreach assistant into a supply-chain-aware agent workflow that links supplier communication with inventory risk, logistics recovery, procurement judgment, and sustainability review.