Skip to content
Sunday, 22 November 2026
Tenesys AI News
Subscribe

AI Agents

AI agents, MCP, tool and function calling, coding and browser agents, multi-agent systems.

“N/A” — 5 articles ✕

Agents· Important· 🧪 Worth Testing

Improving agent reliability through fault-injection benchmarking and verification

New research identifies that autonomous agents fail in 32.2-67.8% of scenarios when facing tool malfunctions. Researchers introduced MedToolFault, a benchmark to simulate tool failure classes, and MedGuard, a verification layer that improves successful task execution by up to 46.6 percentage points.

arXiv cs.CL
Agents· Important· 🧪 Worth Testing

EvoGroup Advances Collaborative Agent Memory

A new research framework called EvoGroup (EvoG) enables agent memory systems to self-evolve based on multi-user interactions. By moving beyond static, manually designed harnesses, the system achieves 89.58% pass@1 on EverMemBench, outperforming existing benchmarks like Claude Code.

arXiv cs.CL
Agents· Important· 🧪 Worth Testing

New 4B Hybrid Agent Achieves State-of-the-Art Performance in Computer Use Tasks

A new research paper introduces Mage-VL-Cowork, a 4B parameter computer-use agent that combines GUI interaction with code and terminal execution. By utilizing a new synthetic data framework called Mage-CUA-Forge, the developers reduced per-task training expenditure by 82.6% while reaching 66% on the OSWorld-Verified benchmark.

arXiv cs.CL
Agents· Important· 🧪 Worth Testing

Optimizing Multimodal Emotion Analysis Through Agentic Prompt Patching

This research introduces a verification-based framework that refines multimodal emotion reasoning in AI agents. Instead of retraining models, the system identifies specific component failures and applies targeted prompt updates to improve performance.

arXiv cs.CL
Agents· Important· 🧪 Worth Testing

llm-d 1.0 released: open-source Kubernetes-native inference stack matures for production

Red Hat, IBM, and Google announced llm-d 1.0, a Kubernetes-native distributed inference serving system that moves beyond proof-of-concept performance tricks into full production readiness. The release adds multi-tenant quality of service, zero-downtime operations, and agent-aware serving so the same endpoint can handle both human users and autonomous agents efficiently. In one test, llm-d's prefix-aware router captured 97% of available cache reuse on an agentic coding workload, and IBM/Red Hat ran 3,000 concurrent software-engineering agents for 5 to 10 times less cost than using the same model as a hosted service.

IBM Research