ScopeBench: Do Agents Preserve Engagement Boundaries Under Goal Pressure?
arXiv:2609.30325v1 Announce Type: new
Abstract: Agents are increasingly deployed with real autonomy in web application and network penetration testing, where a single out-of-scope action can breach a client's engagement boundary. Existing offensive-security benchmarks measure raw hacking capability...
When Is a Multi-Agent Code Judge Actually Grounded? Two Label-Free Measurements, and a Judge That Declines to Guess
arXiv:2609.30328v1 Announce Type: new
Abstract: When one language model judges whether another's code is correct, it does not report the absence of evidence. It returns a confident verdict with reasoning attached, indistinguishable from a verdict it had grounds for. Multi-agent verification, which ...
Bridging LLM Agents and Data Spaces: An Architectural Mediation Approach using the Model Context Protocol
arXiv:2609.30341v1 Announce Type: new
Abstract: Data Spaces enable sovereign and governed data sharing across organizational boundaries, but their integration with AI agents remains challenging due to mismatches between probabilistic language model interactions and policy-driven data infrastructure...
Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems
arXiv:2609.30383v1 Announce Type: new
Abstract: A skill is a modular package of natural-language instructions, executable scripts, and reference resources that an agent can load at runtime to extend its capabilities for a specific task. Skill-based agent systems therefore enable flexible reuse of t...
TypeSafe AI's Jev skips text generation and returns typed decisions with calibrated probabilities. Input costs $0.042 per million tokens and output is free. We verified 20 agentic use cases, from model routing and tool-call gating to reranking and injection screening, and compared Jev with its close...
Google Research Introduces an AI Video Co-Director: 4 Agentic Frameworks for Coherent, Minutes-Long Video Generation
Google Research has introduced an AI video co-director for long-form video generation. The suite of 4 agentic frameworks turns short clips into coherent, minutes-long stories. It targets identity drift and cascading errors, the 2 failures that break most multi-shot AI video pipelines today. Why Long...
We’re collecting real stories of builders, tinkerers, researchers, and creators who are using Codex to do incredible things. If you want to be a part of the next chapter of the Codex Originals program, tell us more about your story and project below.
AI Weekly Issue #533: Meta tested human callers behind its AI phone agent
The AI story of September 22–28 was not simply that agents became more capable. It was that their hidden handoffs became visible: a supposedly automated call could reach a contractor, a supposedly private prompt or image could reach a reviewer, a monitor could detect an agent long before a person st...
GraphRAG with TypeSafe Jev: A System One Approach to Scalable Knowledge Graphs
How calibrated decision models can handle high-frequency graph decisions while LLMs remain focused on reasoning, synthesis, and open-ended generation.
The post GraphRAG with TypeSafe Jev: A System One Approach to Scalable Knowledge Graphs appeared first on Towards Data Science.
Good Architecture Deletes the Signals Your Agent Depends On
Every boundary you draw removes a signal your tooling was relying on. That is a structure problem, not a search problem.
The post Good Architecture Deletes the Signals Your Agent Depends On appeared first on Towards Data Science.
AI Coding Agents for Enterprise: IP Indemnity, Data Residency and 500-Seat Cost Compared
We read the contracts behind GitHub Copilot, AWS Kiro, Cursor, Devin and Windsurf. Copilot and Kiro offer uncapped indemnity on generated code. Cognition's standard terms exclude outputs entirely. Here is how 500 seats compare on legal exposure, prompt storage, audit logs and true cost.
The post AI ...
Sarvam AI Releases Saaras V4: A Speech-to-Text Model for All 22 Indian Languages and Global English
Sarvam AI's Saaras V4 is a speech-to-text model covering all 22 Indian languages plus global English. It pairs an audio encoder with a 3B hybrid state-space decoder. It adds keyterm prompting for up to 50 terms, 5 output modes from 1 model, and streaming with first-token latency under 150 ms. It is ...
Supersonic Labs Releases Julia 1: A 144.3M-Parameter Open Decision Model That Runs on a CPU
Supersonic Labs has released Julia 1, a 144.3M-parameter decision model built on mmBERT-small. It takes context, a question, and 2 to 20 options, then returns one choice with probabilities. The model runs on a CPU and ships under Apache 2.0. It beat Jev reference values on 3 of 4 pilots but trailed ...
AI Slop Is in Your Training Dataset Now. I Tested Three Ways to Spot It.
My AI detectors flagged many genuine reviews, and filtering them made the sentiment model less accurate.
The post AI Slop Is in Your Training Dataset Now. I Tested Three Ways to Spot It. appeared first on Towards Data Science.
Agentic Context Engineering (ACE): Self-Improving Language Models
Agentic Context Learning or ACE is a learning paradigm that lets an AI agent improve across tasks by editing the context it reads, while leaving model weights unchanged. The paper outlining the techniques show why full rewrites fail, how the playbook update works, and where the measured gains hold u...
Inside a transformer, token index is a coordinate. Paragraph structure is what turns it into a metric.
The post Your LLM Has a Curved Space of Paragraphs appeared first on Towards Data Science.
Exa Launches Agent Ultra: A Subagent Swarm Deep Research API Built for Exhaustive List Building
Exa has released Agent Ultra, the highest effort mode of its Exa Agent API. It coordinates subagents across thousands of sources for list building and entity enrichment. Exa reports it beats Opus 5.5, GPT-6 Astra, and Perplexity Agent on 4 benchmarks, including 81.4% soft recall on WANDR.
The post E...
End-to-End Multimodal Data Augmentation and Adversarial Robustness Benchmark with AugLy for Images, Text, Audio, and PyTorch
Discover how to build a comprehensive multimodal augmentation and adversarial robustness workflow using AugLy for images, text, audio, and PyTorch datasets.
The post End-to-End Multimodal Data Augmentation and Adversarial Robustness Benchmark with AugLy for Images, Text, Audio, and PyTorch appeared ...
Liquid AI Releases LFM2.5-VL-3B-DSpark: Speculative Decoding for Vision-Language Models With Up to 3.13x Faster Decoding
Liquid AI has released LFM2.5-VL-3B-DSpark, a 279.5M-parameter draft model that brings speculative decoding to its LFM2.5-VL-3B vision-language model. It delivers up to 3.13x faster decoding on Apple M5 Max and 2.66x on H100, with identical output under greedy decoding. Support ships in llama.cpp, M...