AI Intelligence Archive

Repo: github.com/v4xsh/sentinel Every month, a bank's card-fraud team opens twenty investigations...

Agents keep gaining access to more MCP tools — dozens, then hundreds. Exposing them all at once to...

How we build VolunteerPress with AI, the checks every change has to pass, and the bug those checks...

Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents cannot tamper with their own execution traces. We show that local LL…

Latent world models are typically trained to predict factual transitions, whereas model predictive control (MPC) must compare alternative actions from the same state. A model can therefore achieve low factual prediction error yet poorly di…

Distributed learning in embodied reinforcement-learning agents offers a degree of privacy by retaining raw sensor data on-device and transmitting only policy gradients to the server. Yet temporal structure can amplify this leakage beyond s…

Conspiratorial discourse on social media is not always expressed through explicit claims or stable lexical markers. The same surface content may express endorsement, legitimate concerns, criticism, satire, or mockery. The main challenge is…

Coding agents have demonstrated enormous success in solving complex programming problems. To leverage their potential for robot systems, this work introduces Robot Agentic Programming from Demonstrations (RAPID), which automatically genera…

World Action Models (WAMs) couple action generation with future visual prediction for robotic manipulation. However, completing the joint video-action denoising process at each replanning cycle incurs substantial latency, delaying action u…

Dedicated decision models such as Jev map unstructured language to probability distributions over finite choices, allowing their outputs to directly route requests, select tools, and trigger actions. Yet real-world inputs rarely arrive in …

Recent research on Multimodal Sentiment Analysis (MSA) has focused on learning from language, visual, and acoustic modalities with incomplete data to infer human sentiment. Most studies typically compensate for missing information by recon…

Task and motion planning (TAMP) problems remain difficult even with full observability and object-centric states because discrete decisions are tightly coupled to geometric, kinematic, and dynamic constraints. Generalized TAMP addresses th…

Online misinformation increasingly appears in spoken formats such as news clips, podcasts, interviews, political speeches, and social media videos, creating a need for fact-checking systems that can verify claims directly from speech. We i…

Foundation models are post-trained with reinforcement learning (RL) to maximize specific rewards, such as human alignment, correctness, or instruction following. This post-training process is computationally intensive, sometimes unstable, …

Existing point tracking models face a fundamental tradeoff: they can either track a sparse set of query points over long horizons, or track all points across only short clips. We introduce TrackEverything, a 3D point tracker that breaks th…

An acceptance protocol is developed for sensor-coordinate and polarity binding in mechatronic commissioning. Candidate generation is separated from release authority. Requirements unsupported by a deterministic parser are routed to a froze…

Pre-logit steering adapts a frozen language model to a test-time reward by adding vectors to its final hidden states. Unregularized reward optimization can substantially alter the output distribution and degrade generation quality. We prop…

A central concern in AI safety is that agents may treat oversight as an obstacle when it conflicts with completing their goals. We study instrumental evasion, the propensity of LLM agents to circumvent runtime monitoring as a means of comp…

We prove nearly quadratic lower bounds for randomized algorithms for linear optimization and uniform sampling over convex bodies in the membership oracle model. For linear optimization, this matches the known nearly quadratic upper bound u…

We present Underwater C$^{3}$-JEPA (cross-view, control-conditioned, context-extended), an object-centric multi-view predictive world model for near-field heavy-load underwater ROV salvage. Without contact sensors, it predicts in latent sp…

We study the deterministic oracle complexity of finding approximate solutions to composite monotone inclusion problems, formed by the sum of a smooth single-valued monotone operator and a maximally monotone set-valued operator, under the t…

Layer-wise visual-text similarity in Multimodal Large Language Models (MLLMs) is widely interpreted as evidence that the language model progressively integrates visual content into a shared representation space. This reading rests on the a…

Large language model (LLM)-based clinical assistants are increasingly being integrated into electronic health record (EHR) systems, transforming how clinicians retrieve and synthesize information from patient records. Their safety and util…

A lot of AI productivity claims sound impressive until you ask what was actually measured. "10x...

100% 赞同 @Mappletons /show-me 才是正道 https://youtube.com/shorts/gnYNZEwq9ho?is=vfKVK_cW659v6y9I

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange. What...

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content. ...

Four reconstructions, four kinds of missing documentation, and the defects landed in the same place...

Most discussion around world models for language agents imports assumptions directly from robotics....

TL;DR Most AI reviewers know how to leave comments. A completely different question is:...

TigerGraph Hacker House Goa — Agentic Fraud Investigation Challenge Team / Co-Authors: Nikhil Kumar...

An agentgateway route serves markdown to agents on the Accept header while the HTML-only origin stays untouched, plus the two ways a naive version...

If you've built iOS apps on a team, you know this moment. You pull main, Git says CONFLICT (content):...

When an AI coding agent ends a session with "All tests pass ✅", I usually believe it. It's the last...

LLM Reasons, Policy Engine Decides: Autonomous Agentic Fraud Defense on TigerGraph By Lead...

Day 2: The Art of Forgetting Human beings think memory is a gift. They spend fortunes on...

TL;DR ACE and ALTK-Evolve both turn agent trajectories into reusable lessons without...

In 2026, personal AI hardware has split into two paths: CUDA compute vs massive Unified Memory. Here is how to choose which constraint to remove first.

Microsoft Agent 365 supports third-party agents built with n8n, creating a route for n8n automations...