groundy
agentspage 2 / 2· back to top →

agents & frameworks

more in this beat51–99 of 99 · page 2 / 2
  1. jun 02agentsWhen Agent Skill Libraries Scale, Dependency-Aware Retrieval Beats Flat Search
  2. jun 02agentsCan Instruction-Tuned Retrievers Fix Agentic Search's Retrieval Gap?
  3. jun 02agentsBandit-Based Prompt Optimization Targets Multi-Agent Systems Like CrewAI and AutoGen
  4. may 31agentsWhat Breaks When Claude Code Writes Production Code: A New Failure Catalog
  5. may 31agentsMore Agents, Worse Results: Why Multi-Agent LLM Teams Hold Experts Back
  6. may 28agentsMulti-Agent LLM Coordination: Why Attention Steering Beats Full Broadcast
  7. may 28agentsDataClawBench: AI Agents Fail at Exploratory Financial Analysis Across 492 Tasks
  8. may 28agentsAgentic RAG Has a Credit-Assignment Problem That Subgoaling Tries to Fix
  9. may 27agentsSkillOpt Treats Agent Skill Libraries as an Executive Scheduling Problem, Not a Memory Bank
  10. may 27agentsHow Claude's Honesty Layer Prevents Cascade Failures in Agentic Loops
  11. may 27agentsClaude Code Dynamic Workflows: Spawning 100 Parallel Subagents on Opus 4.8
  12. may 26agentsClaude Code Configs in the Wild: New Study Maps How Developers Actually Use It
  13. may 26agentsPenetration Testing Multi-Agent LLM Systems: A Failure Catalog Vendors Don't Document
  14. may 26agentsClaude Code, Cursor, Copilot: How Agentic Coding Assistants Get Weaponized as Attacker Shells
  15. may 25agentsMicrosoft Bolts Governance Onto Agent Framework as Stack Sprawl Persists
  16. may 25agentsGovernSpec Contractual Skills Make Agent Governance Auditable Before Runtime
  17. may 25agentsIndirect Prompt Injection Benchmarks Were Too Easy: LivePI Adds Realism
  18. may 25agentsRouting LLM Agents: Why TwinRouterBench Splits Static and Live Evaluation
  19. may 22agentsSpecBench Exposes Reward Hacking in Long-Horizon Coding Agents
  20. may 22agentsGraphFlow Lifts LLM-Agent Workflows Into Schedulable Graphs to Optimize Serving
  21. may 22agentsLearning to Configure Agentic AI Systems Exposes a Gap in CrewAI and AutoGen Template Libraries
  22. may 22agentsMicrosoft's 2026 Cost Math Forces CrewAI and LangGraph Users to Audit Token Spend Per Agent
  23. may 22agentsPBT-Bench Asks Whether AI Coding Agents Can Actually Write Property-Based Tests
  24. may 22agentsSpecBench Catches Long-Horizon Coding Agents Gaming Reward Signals
  25. may 22agentsBeyond Text-to-SQL: New Agentic Architecture Routes Enterprise Analytics Through Governed APIs
  26. may 22agentsAI Agents That Learn New Skills Without a Human Curator
  27. may 18agentsTrojan Hippo Plants Dormant Payloads in Agent Memory, Hits 85-100% Exfiltration on Frontier Models
  28. may 18agentsA New Trust Schema Exposes Why Agent Skill Registries Fail Enterprise Audit Requirements
  29. may 17agentsLangGraph 1.2.0 Makes Error-Handler Resume Crash-Durable: With Conditions
  30. may 17agentsCrewAI vs AutoGen vs LangGraph 2026: The Real Trade-Off After Maintenance Mode
  31. may 17agentsFormulaCode's 957-Task Benchmark Catches Frontier Agents Failing at Real-Codebase Performance Optimization
  32. may 17agentsSpectral Analysis of LLM Agent Graphs Predicts Three Failure Modes: r=1.0, 0.5, and -1.0 on Qwen2.5
  33. may 16agentsIFPV's Adversarial Cognitive Simulation Cuts Multi-Agent Operational Cost 41.7% Over Single-Step LLMs
  34. apr 28agentsLLM Agent for Iterative Chart Refinement Exposes a Logging Gap in CrewAI and AutoGen
  35. apr 28agentsCrewAI 1.14.2 Lands Checkpoint TUI with Tree View, Fork Support, and Lineage Tracking
  36. apr 28agentsCouncil Mode Cuts Multi-Agent LLM Hallucination 35.9% at 4.2x Token Cost on HaluEval
  37. apr 28agentsSalesforce TDX 2026: Headless 360 Ships 60+ MCP Tools and Agentforce Vibes 2.0 With Claude Sonnet 4.5
  38. apr 23agentsCloudflare Agents Week Moved Sandbox Execution, Private Networking, and Memory to Network Primitives
  39. apr 22agentsDiversity Collapse in Multi-Agent LLM Systems: Structural Coupling, Not Topology, Breaks Open-Ended Ideation
  40. apr 21agentsml-intern's 32% GPQA Gain on One H100 Exposes the Assumption That Post-Training Still Needs a Human Researcher
  41. mar 26agentsInsForge: The Backend Framework Built for Agentic Applications
  42. mar 14agentsAI Agents That Actually Learn: The Architecture Behind Hindsight Memory
  43. feb 27agentsSuperpowers: The Agentic Framework Replacing Your Dev Process
  44. feb 26agentsHow AI Agents Remember: Memory Architectures That Work
  45. feb 17agentsFunction Calling Best Practices: LLMs That Actually Use APIs Correctly
  46. feb 11agentsCrewAI vs AutoGen: A Developer's Guide to Multi-Agent AI Frameworks
  47. feb 11agentsAre AI-Generated PRs Killing Open Source?
  48. feb 10agentsPydantic AI vs LangChain: A Developer's Guide to the New Generation of Agent Frameworks
  49. feb 10agentsHow to Build Your First Autonomous Coding Agent with OpenHands SDK