Learning and Enforcing Context-Sensitive Control for LLMs

⋅

Controlling the output of Large Language Models (LLMs) through context-sensitive constraints has emerged as a promising approach to overcome the limitations of Context-Free Grammars (CFGs) in guaranteeing generation validity. However, such constraints typically require manual specification — a significant barrier demanding specialized expertise. We introduce a framework that automatically learns context-sensitive constraints from LLM interactions through a two-phase process: syntactic exploration to gather diverse outputs for constraint learning, followed by constraint exploitation to enforce these learned rules during […]

Ver mais

Liked Liked
Building a Critic-Agent Loop: Scores, Refinement, and Guardrails

Building a Critic-Agent Loop: Scores, Refinement, and Guardrails

⋅

Author(s): Nitingummidela Originally published on Towards AI. Building a Critic-Agent Loop: Scores, Refinement, and Guardrails A friendlier take on the guarded critic-agent loop — Worker Bot drafts, Critic Bot scores it, and only passing work ships; anything that fails three times gets escalated to a human instead of looping forever. This is the hands-on companion to Part 1: The Critic Agent — Teach Your AI to Check Its Own Work. There, we covered the idea: a separate critic […]

Ver mais

Liked Liked

Adaptive Retrieval helps Reasoning in LLMs — but mostly if it’s not used

⋅

arXiv:2602.07213v1 Announce Type: new Abstract: Large Language Models (LLMs) often falter in complex reasoning tasks due to their static, parametric knowledge, leading to hallucinations and poor performance in specialized domains like mathematics. This work explores a fundamental principle for enhancing generative models: treating retrieval as a form of dynamic in-context learning. We test an adaptive retrieval-augmented architecture where an LLM agent actively decides when to query an external knowledge base during its reasoning process. We compare this adaptive […]

Ver mais

Liked Liked
A Jupiter-size planet that escaped its star's death

A Jupiter-size planet that escaped its star’s death

⋅

WD 1856 b is the only confirmed case of a planet that survived the death of a Sun-like star. It’s a Jupiter-size world orbiting a white dwarf—the burned-out remnant of a Sun-like star. Now, a team of astronomers has used the James Webb Space Telescope to take a closer look at this planet for the first time, and what they found makes an already strange system even stranger. A feeding frenzy WD 1856 b was an accidental discovery. […]

Ver mais

Liked Liked
Indian med student rakes in thousands with AI-generated MAGA hottie

Indian med student rakes in thousands with AI-generated MAGA hottie

⋅

Like many medical school students, Sam was broke. The 22-year-old aspiring orthopedic surgeon from northern India got some money from his parents, but he says he spent most of it subsidizing his licensing exams, and he’s still saving up to hopefully emigrate to the US after graduation. So he started searching for ways to make additional money online. Sam, who requested a pseudonym to avoid jeopardizing his medical career and immigration status, tried a few things, with varying […]

Ver mais

Liked Liked
Narwhals become quieter as the Arctic Ocean grows louder

Narwhals become quieter as the Arctic Ocean grows louder

⋅

For most of their evolutionary history, narwhals have relied more on sound than sight to survive in the Arctic’s dark icy waters. The speckled toothed whales—sometimes referred to as “unicorns of the sea” for the long, spiral tusks that protrude from the heads of males—navigate, hunt, and communicate using echolocation. By emitting a series of calls, whistles, and high frequency clicks—as many as a thousand per second—and listening for the echoes that bounce back, they are able to […]

Ver mais

Liked Liked
The new top banana in AI image generation

The new top banana in AI image generation

⋅

Read Online | Sign Up | Advertise Good morning, {{ first_name | AI enthusiasts }}. When Google launched the original Nano Banana last August, it set the bar for AI image generation — now, the sequel is raising it. The new Nano Banana 2 just reclaimed the text-to-image crown across leaderboards, while also effectively ending the tradeoff between top-tier quality and affordability in the process. In today’s AI rundown: Google’s Nano Banana 2 claims No. 1 at half […]

Ver mais

Liked Liked

Precedence-Constrained Decision Trees and Coverings

⋅

arXiv:2602.21312v1 Announce Type: new Abstract: This work considers a number of optimization problems and reductive relations between them. The two main problems we are interested in are the emph{Optimal Decision Tree} and emph{Set Cover}. We study these two fundamental tasks under precedence constraints, that is, if a test (or set) $X$ is a predecessor of $Y$, then in any feasible decision tree $X$ needs to be an ancestor of $Y$ (or respectively, if $Y$ is added to set […]

Ver mais

Liked Liked

Mechanism Design for Quality-Preserving LLM Advertising

⋅

arXiv:2605.10964v1 Announce Type: new Abstract: Embedding advertisements into large language model (LLM) outputs introduces a fundamental tension: revenue optimization can distort content and degrade user experience. Existing approaches largely ignore this trade-off, often forcing irrelevant ads into responses. We propose a quality-preserving auction framework that explicitly integrates content fidelity into the mechanism design. Built on retrieval-augmented generation (RAG), our approach treats organic content as a reference and derives an endogenous reserve price that screens out ads with non-positive […]

Ver mais

Liked Liked
Bank of England reviews AI rules for agentic AI in finance

Bank of England reviews AI rules for agentic AI in finance

⋅

The Bank of England is reviewing whether existing rules can cover the use of agentic AI in finance, including payments, trading, cybersecurity, and operations. Deputy Governor Sarah Breeden said existing regulatory frameworks were not designed for AI agents that can act without direct human instruction. Speaking at the European Central Bank Forum on central banking in Portugal, she said relying on human oversight for every action by these systems is unlikely to be practical. Breeden said current frameworks […]

Ver mais

Liked Liked

Load More

↑

Digitado © 2026