Skip to content

Related concepts: Agent Memory Tool Use Context Engineering Code Agents Frequently mentioned with: arXiv OpenAI Google Hugging Face Anthropic Recent briefs: 2026-11-18 2026-11-17 2026-11-16 2026-11-15 2026-11-14

Related: Agent Memory Tool Use Context Engineering Code Agents

This is the Agents concept page (definitions and fundamentals). For dated developments, see the Agents Topic hub.

Recent Updates

  • 2026-11-17: Agentic On-Policy Distillation Implicitly Reshapes LLMs’ ReAct Patterns (cs.AI updates on arXiv.org) · arxiv.org — Hugging Face
  • 2026-11-17: Auditable Authorization for LLM Agents Across Model, Harness, and Workflow Layers (cs.AI updates on arXiv.org) · arxiv.org — arXiv · CrewAI · n8n
  • 2026-11-17: Beveridge: Open-Weight Decision Models Delivering Calibrated Probabilities for Structured Decisions (cs.LG updates on arXiv.org) · arxiv.org — arXiv · NVIDIA · Apple · Hugging Face ModernBERT-large · Gemma-4-26B-A4B Beveridge-Large-C Beveridge-Pro-C Beveridge-Pro-C-Web
  • 2026-11-17: SPLICE: Structured Prompt Local Iterative Combinatorial Evolution (cs.AI updates on arXiv.org) · arxiv.org
  • 2026-11-17: Agents Cannot Hand Over What They Have Not Yet Understood (cs.AI updates on arXiv.org) · arxiv.org — Hugging Face · Connected Papers · Litmaps · scite · alphaXiv · CatalyzeX · DagsHub · Gotit.pub · ScienceCast · CORE · arXivLabs
  • 2026-11-17: OpenAI and Anthropic Publish Architectural and Security Guides for Persistent Agent Systems (LLM под капотом) · developers.openai.com — OpenAI · Anthropic · BitGN
  • 2026-11-17: Google Launches Gemini 4 Hydrogen Model and Robotics Plugin for Antigravity (Google Developers Blog) · developers.googleblog.com — Google · Artificial Analysis · Gemini 4 Hydrogen · Gemini 4 Argon · Gemini 4 Carbon Gemini Robotics ER 2
  • 2026-11-17: StarSling Launches Self-Improving CI Runners for Agent-Volume Repositories (Hacker News) · starsling.dev — StarSling Y Combinator · GitHub · AMD · Mastra Better Auth Partcl
  • 2026-11-17: Google AI Studio Adds Full-Stack Android App Generation and Play Store Publishing (Google Developers Blog) · developers.googleblog.com — Google · YouTube · Gemini 4 Carbon · Gemini 4 Hydrogen
  • 2026-11-18: OpenAI Launches GPT-6.2 Astra and Sol with Agent and Coding Upgrades (量子位) · qbitai.com — OpenAI · Artificial Analysis · Cognition · GPT-6.2 Astra · GPT-6.2 Sol · GPT-6 Astra · Claude Fable 5.2
  • 2026-11-18: JET: Just-Enough Exploration Tuning for Efficient Tool-Calling Agents in Repository-Level QA (cs.CL updates on arXiv.org) · arxiv.org — Hugging Face
  • 2026-11-18: Separating Confidence, Abstention, and Recovery in LLM Agent Verification (cs.CL updates on arXiv.org) · arxiv.org — arXiv · alphaXiv · CatalyzeX · DagsHub · Gotit.pub · Hugging Face · ScienceCast · CORE
  • 2026-11-18: Testing the Overfitted Brain Hypothesis on an LLM Agent with Text Memory (cs.CL updates on arXiv.org) · arxiv.org — Hugging Face Hoel · Claude Opus 5.5
  • 2026-11-18: FieldGuide: Topic-Hierarchical Corpus Maps for Token-Efficient Agentic Document Exploration (cs.CL updates on arXiv.org) · arxiv.org — Hugging Face Chicago Police Department
  • 2026-11-18: A Unifying Framework for Self-Improving Agent Harnesses (cs.AI updates on arXiv.org) · arxiv.org — arXiv · Hugging Face · Connected Papers · Litmaps · scite · CatalyzeX · DagsHub · Gotit.pub · ScienceCast · CORE
  • 2026-11-18: Multi-Agent Memory Inconsistency and Factual Conflicts in LLM Agents (cs.AI updates on arXiv.org) · arxiv.org — Harvey
  • 2026-11-18: Minimal RAG Memory Architecture Matches Complex Agent Memory Baselines Across Benchmarks (cs.AI updates on arXiv.org) · arxiv.org — arXiv
  • 2026-11-18: LLM Trading Agents Suffer from Look-Ahead Bias and Rely on Memorized Training Data (cs.AI updates on arXiv.org) · arxiv.org — arXiv · Gemini · GPT
  • 2026-11-18: Evidence Governance Framework Addresses Evidence Hijacking in Tool-Augmented Medical Agents (cs.AI updates on arXiv.org) · arxiv.org — arXivLabs · Connected Papers · Litmaps · scite · alphaXiv · CatalyzeX · DagsHub · Gotit.pub · Hugging Face · ScienceCast · CORE
  • 2026-11-18: RegimeCouncil: Paired-Evidence Routing for Memory Conflict Governance in LLM Agents (cs.AI updates on arXiv.org) · arxiv.org — Qwen3-30B-A3B · GPT-4o
  • 2026-11-18: EvoDisco: Strategy Discovery for Evolving Agent Memory (cs.AI updates on arXiv.org) · arxiv.org — Hugging Face
  • 2026-11-18: ATLAS-Finance: Benchmarking AI Agents on Multi-Application Banking Tasks (cs.AI updates on arXiv.org) · arxiv.org — arXiv · Hugging Face · DagsHub · ScienceCast · alphaXiv · CatalyzeX · Connected Papers · Litmaps · scite · Gotit.pub · CORE · Claude Opus · Fable
  • 2026-11-18: Reversibility Classes for AI Agent Actions Across MCP Tool Ecosystems (cs.AI updates on arXiv.org) · arxiv.org — arXiv · Hugging Face
  • 2026-11-18: Task-Conditioned Agent Resource Composition via Retrieval and Bundle-Aware Critics (cs.AI updates on arXiv.org) · arxiv.org
  • 2026-11-18: SkillBuffBench: Benchmark for Evaluating Agent Skills Across Harnesses, Models, and Memory (cs.AI updates on arXiv.org) · arxiv.org — Anthropic · Google · OpenAI · arXivLabs

FAQ

What is Agents?

AI agents are LLM-driven systems that can plan, call tools, inspect results, and iterate toward a goal. GROUNDING tracks agent architectures, benchmarks, tool use, browser agents, coding agents, and reliability patterns.

Related concepts tracked by the radar include Agent Memory, Tool Use, Context Engineering, Code Agents.

What does this Agents page track?

Dated updates, papers, and mentions of Agents collected by the GROUNDING radar, most recently on 2026-11-18.