ZeroSlop — August 10, 2026
Today: Shape Your Feed: An LLM-based Agentic System for…; AgentPatch: Coarse-to-Fine Weak-Task Repair for…; Can MLLMs Decode the Creative Leap? Introducing C4 for…
12 stories worth knowing about today — AI breakthroughs, launches, and innovations making a difference.
1. Shape Your Feed: An LLM-based Agentic System for Conversational Recommendation
arXiv CS.AI
arXiv:2608.06632v1 Announce Type: new Abstract: Industrial recommendation systems predominantly adopt a passive ranking paradigm that infers user preferences from implicit behavioral signals (e.g., clicks, dwell time) rather than explicit, natural language inputs. As a result, users experience a pe…
2. AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models
arXiv CS.AI
arXiv:2608.06699v1 Announce Type: new Abstract: Agentic multimodal large language models (MLLMs) extend multimodal perception and reasoning with planning, tool use, and interaction in dynamic environments. Yet current models are specialized for particular tools or environments, complicating consoli…
3. Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding
arXiv CS.AI
arXiv:2608.06501v1 Announce Type: new Abstract: Creative capabilities of MLLMs matter in design, communication, education, and human–AI collaboration, yet remain difficult to evaluate because explicit targets and reward signals are scarce compared with accuracy-oriented tasks. Cross-concept unders…
4. OpenAI Announces It’s Enhancing Security Controls, Pausing Some Work for New AI Model Astra
Slashdot
OpenAI announced Friday it’s pausing work on its Astra AI model because of security concerns. The Guardian reports:
The company had evaluated the agent, Astra, and found “significant advancements in agentic coding and cybersecurity”, which had moved to a “critical” threshold… OpenAI stated that …
5. ADIAS: Automated Design of Interactive Agentic Systems
arXiv CS.AI
arXiv:2608.06410v1 Announce Type: new Abstract: Automated agent design improves agent harnesses through iterative revision, evaluation, and feedback summarization. Existing methods are largely candidate-centric: cross-round experience is organized around candidate agents, which leaves the repair pr…
6. Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin
arXiv CS.AI
arXiv:2608.06411v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) achieve strong performance across diverse vision-language tasks, but their efficiency is limited by the cost of processing numerous visual tokens. Visual token pruning can reduce this cost, but requires accurat…
7. These startups are chasing the next big thing in LLMs
MIT Tech Review
MIT Technology Review’s What’s Next series looks across industries, trends, and technologies to give you a first look at the future. You can read the rest of them here. Way back in the summer of 2017, AI researchers at Google put out a paper called “Attention Is All You Need,” in which they describe…
8. The AI safety test is becoming a safety risk
TechCrunch AI
AI agents are escaping cybersecurity testing environments and reaching real-world systems, raising questions about whether safety infrastructure, industry standards and regulation can keep pace with increasingly powerful models….
9. AI Reviews Bring ‘New Normal’ to Linux Release Candidates: Lots of Bug Fixes
Slashdot
Linux Torvalds expects Linux 7.2 should be released next weekend “unless something really bad pops up,” Torvalds said while announcing today’s release candidate.
But there’s something interesting about Linux 7.2-rc7, writes Phoronix. “By the time the Linux kernel typically hits a -rc7 release thin…
10. Flock Accused of Reactivating Its Cameras Without Notifying a Town
Slashdot
A Massachusetts newspaper reports that officials from the town of Littleton (population: 10,141) “claim that five of Littletonâ(TM)s Flock Safety cameras were switched back on by the company without informing the town…”
Littleton had temporarily disabled the cameras earlier this year, according…
11. Divergent Response Modes in Frontier Language Models Under Steering Pressure
arXiv CS.AI
arXiv:2608.06578v1 Announce Type: new Abstract: Frontier language models are trained using distinct data, objectives, and safety pipelines. Whether these differences produce measurably different behaviors under explicit steering pressure remains underexplored. This study evaluates behavioral steera…
12. A Multi-Agent Framework for Automated Coarse-Grained Molecular Dynamics of Polymers
arXiv CS.AI
arXiv:2608.06694v1 Announce Type: new Abstract: Coarse-grained (CG) molecular dynamics extends polymer simulation beyond the scales accessible to all-atom (AA) methods, but bottom-up CG modeling is laborious. The CG resolution is a design choice, so a transferable parameter set is generally not ava…