Tuesday 15 September 2026Paper No. 1,386

Evening EditionRSS

ZOTPAPER

News without the noise

Research

Digests of notable academic papers, primarily from arXiv

212 articles · page 3 of 3

All Agent Harnesses Tools & MCP Multi-Agent Systems Creative Agents Memory & Planning Safety & Evals RL for Agents AI & ML

Viewgrid list compact

AI progress may continue past AGI toward superintelligence, not stop

New benchmark standardizes evaluation of coding agent harnesses

Decentralized agents with shared context outperform centralized orchestration

Pruning context to recent tool calls improves agent reliability and efficiency

Multi-agent orchestration generates 3D scenes from single images

New benchmark reveals coordination as distinct bottleneck for LLM agents

Conversational image editing agent learns interpretable tool use

VLMs improve spatial reasoning by actively imagining novel views with a world simulator

First systematic characterization of agent memory systems across long-horizon tasks

Memory as state management instead of semantic retrieval improves long-horizon agents

Self-supervised method improves agent harnesses using past trajectories

RL with live server state boosts multi-step tool use in LLMs

Multi-agent framework coordinates narrative and visual consistency for long-form video

Evolutionary training harness co-evolves with LLM policies for RL

Code-driven agents generate images via sketching and texturing stages

First measurement study reveals widespread authentication flaws in remote MCP servers

Benchmark reveals frontier LLM monitors miss most covert attacks by coding agents

Proposing a workflow store to harden AI agents against failure

A multi-agent framework for coherent video storytelling via global optimization

Unified visual-generation agentic model outperforms larger closed-source models