This is GROUNDING’s Agents topic hub: a running, dated log of developments the radar has mapped to Agents, refreshed as new signal arrives.
This is the Agents Topic hub (dated developments). For definitions and fundamentals, see the Agents concept page.
Key Developments
- 2026-09-09: SurveyAgent-HKA: Multi-agent framework for scientific survey generation with LLM and human knowledge (breakingnewsofficial) · arxiv.org Agents
- 2026-09-09: EdgeMem: LLM-Free Agent Memory Construction and Retrieval via Evidence-Preserving Multi-Anchor Hypergraph (breakingnewsofficial) · arxiv.org Agent Memory
- 2026-09-09: Multi-turn LLM Degradation: How Assistant-Generated History Shapes Downstream Behavior (breakingnewsofficial) · arxiv.org Agent Memory
- 2026-09-09: AtomCite: Verification and Correction of Supplied Page-Level Citations in Multi-Page Documents (breakingnewsofficial) · arxiv.org Agents Anthropic · OpenAI · Google · Claude · Gemini · GPT
- 2026-09-09: AutoFyn: Expert Iteration for Long-Horizon Agents via Persistent State Adaptation (breakingnewsofficial) · arxiv.org Agents Agent Memory AutoFyn Next.js MetaMask · pnpm · Warp · LiteLLM · Langflow · Open WebUI
- 2026-09-09: MERIT: Cost-Aware Evaluation of Memory in Tool-Using LLM Agents (breakingnewsofficial) · arxiv.org Agent Memory Agents Tool Use OpenAI · Anthropic · GPT-4.1-mini · GPT-4.1 · Claude Haiku 4.5 · Claude Sonnet 5
- 2026-09-09: XunFei Spark X2.5: End-to-End Agentic Task Delivery from Creative Prompts to Production Code (breakingnewsofficial) · qbitai.com Agents Tool Use XunFei OpenAI · Anthropic · NVIDIA · Hugging Face · DeepSeek Spark X2.5 · Claude
- 2026-09-09: Geiger – See every AI agent on your machine and what it can touch (breakingnewsofficial) · github.com Agents MCP Anthropic 21st-dev
- 2026-09-09: OtoDock: Self-hosted agent platform with persistent memory and team coordination (breakingnewsofficial) · github.com Agents Agent Memory Tool Use Anthropic · OpenAI · Twilio
- 2026-09-10: Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMs (breakingnewsofficial) · arxiv.org Agent Memory kimi-k2.5
- 2026-09-10: Separating Agent Storage from Usage: RD-Forget Framework for Persistent Memory Management (breakingnewsofficial) · arxiv.org Agent Memory Agents
- 2026-09-10: Kernel-Managed Shared Memory for Multi-Agent System Personalization (breakingnewsofficial) · arxiv.org Agent Memory Agents OpenAI · Meta · Alibaba · Mem0 · GPT-4o · Llama-3.1:8B · Qwen 2.5 7B
- 2026-09-10: VLX-VR: An Agentic-Aware Video Reasoning Model (breakingnewsofficial) · arxiv.org Agents Agent Memory VLX-VR
- 2026-09-10: AgentAudit: An Open, Extensible Framework for Full-Lifecycle Trust Evaluation of AI Agents (breakingnewsofficial) · arxiv.org Agents Agent Memory Tool Use OpenAI · Anthropic · Google · Meta Sarvam AI · GPT-5 · Claude Sonnet 5 Sarvam 105B · Llama-3.3-70b · Gemini 2.5 Flash
- 2026-09-10: Procedural Memory Under Change: Reuse and Interference in Controlled Web Tasks (breakingnewsofficial) · arxiv.org Agent Memory Agents Qwen3-8B
- 2026-09-10: ROAM: Robust Organization of Atomic Memories for Agents through Semantic Relations (breakingnewsofficial) · arxiv.org Agent Memory Agents
- 2026-09-10: PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations (breakingnewsofficial) · arxiv.org Agent Memory
- 2026-09-10: ContractEval: Diagnostic Framework for Procedural Instruction Conformance in LLM Agents (breakingnewsofficial) · arxiv.org Agents
- 2026-09-10: State-Path Tool Menus: Learning Execution Routes to Improve Agent Tool Selection (breakingnewsofficial) · arxiv.org Agents Tool Use
- 2026-09-10: Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks (breakingnewsofficial) · arxiv.org Agents
- 2026-09-10: HybridDeepResearch Benchmark Reveals AI Agents Struggle With Web and Database Reasoning (breakingnewsofficial) · arxiv.org Agents Tool Use Snowflake · OpenAI · Anthropic · Hugging Face · GLM-5.2 · Claude Sonnet 4.6 · GPT-5
- 2026-09-10: How AI agents now compress multi-day prototyping into minutes with Codex and tool orchestration (breakingnewsofficial) · t.me Agents Tool Use
- 2026-09-11: Auto-RecSys: Harnessing Autonomous Research Agents for Industry-Scale Recommender Systems (breakingnewsofficial) · arxiv.org Agents Agent Memory
- 2026-09-11: SearchAtlas: Analyzing LLM Search Agent Behavior Through Evidence Graphs (breakingnewsofficial) · arxiv.org Agents
- 2026-09-11: Benchmarking RTK terminal compression: claimed 60% token savings don’t materialize in practice (breakingnewsofficial) · quesma.com Agents Anthropic · JetBrains · OpenRouter · Fable 5 · DeepSeek V4
FAQ
What is the Agents topic?
The Agents topic is GROUNDING’s hub for Agents: a running, dated log of developments, releases, and mentions the radar has tracked, refreshed as new signal arrives.
What does the Agents topic page track?
Key developments the GROUNDING radar mapped to Agents, updated through 2026-09-11.
How current is this page?
The most recent Agents development listed here is dated 2026-09-11; the radar refreshes hourly.