Frameworks

LangGraph / AutoGen / CrewAI 等 Agent 编排框架的演进与实战。

58 articles Categories色 #5B47FB Newest 2026-11-08
Archive · Frameworks 11 articles
Frameworks

Memorilla and the Push for Internal Agent Memory

Memorilla proposes letting LLMs retrieve memories from internal semantic representations, potentially reducing context assembly. However, without public data on memory writes, conflict resolution, deletion, and auditing, it is too early to conclude that it outperforms RAG.

2026-11-07 Source 2026-11-06 8 min 181 views
Frameworks

Five Qwen Agents Beat One Stronger Model

Memdoor used five Qwen3.8-27B instances to outperform Fable 5 on LiveCodeBench Hard. Its team-based workflow offers a practical blueprint for multi-Agent orchestration, shared memory, and result revision.

2026-11-01 Source 2026-10-31 6 min 181 views
Frameworks

Inside Google’s Sleep Framework for Continual Learning

Google Research’s Sleep framework treats learning and memory consolidation as parallel processes, helping language models retain old capabilities as they absorb new data. Its broader implications include a practical memory architecture for long-running Agents that separate online execution from offline consolidation.

2026-10-31 Source 2026-10-28 8 min 181 views
Frameworks

Intelligence Index v5: A Practical Guide to Model Selection

Artificial Analysis has updated its Intelligence Index to compare model intelligence, pricing, and speed. For enterprises, the rankings are only a starting point: real selection also requires workload-specific testing, Agent trajectory analysis, and cost calculations based on actual usage.

2026-10-28 Source 2026-10-28 7 min 181 views
Frameworks

Securing the AI Training Environment Beyond the Model

OpenAI has outlined security controls for its frontier-model training infrastructure, covering access boundaries, monitoring, and auditability. These controls determine how much confidence developers can place in the provenance and deployment of a model.

2026-10-24 Source 2026-10-23 6 min 181 views
Frameworks

Can AI Generate Code for Low-Resource Languages?

OpenAI tested how well models can generate and understand code in low-resource programming languages. The more practical opportunity may be incremental modernization of costly legacy systems, though fully reliable automated migration remains out of reach.

2026-10-21 Source 2026-10-20 4 min 181 views
Frameworks

HybridAgent Moves LLM Reasoning Into Latent Space

Together Computer has open-sourced HybridAgent, an LLM agent that performs chain-of-thought reasoning in vector space before expressing its decisions as tool calls. The release includes code, model weights, and enough training detail to evaluate its practical value and reproduce its results.

2026-10-19 Source 2026-10-18 5 min 181 views