Tagged articles

prompt compression

3 articles · Page 1 of 1

Jul 8, 2026 · Information Security

Prompt Compression Creates a New LLM Vulnerability: HKUST’s Black‑Box Attack Framework COMA (ASE 2026)

The paper reveals that prompt‑compression modules, widely used to reduce token usage in LLM agents, can be exploited to erase critical safety constraints, enabling a black‑box attack called COMA that achieves up to 71% success across multiple compressors and tasks, and proposes isolated compression as an effective defense.

Agentic AICOMAInformation Security

0 likes · 10 min read

Prompt Compression Creates a New LLM Vulnerability: HKUST’s Black‑Box Attack Framework COMA (ASE 2026)

Linyb Geek Road

May 12, 2026 · Artificial Intelligence

10 Open‑Source Tools Cutting AI Agent Costs Ten‑Fold: Prompt Compression, Memory Management, Model Routing

The article explains how AI agents become expensive because they ingest massive, irrelevant context and shows ten open‑source projects—LLMLingua, mem0, LiteLLM, LlamaIndex + Chroma, Letta, Guidance, Aider, tiktoken + ttok—that compress prompts, manage memory, route models dynamically, add retrieval‑augmented generation, and enforce token budgeting, collectively reducing daily token usage by millions and slashing costs dramatically.

AI AgentsModel RoutingOpen source

0 likes · 17 min read

10 Open‑Source Tools Cutting AI Agent Costs Ten‑Fold: Prompt Compression, Memory Management, Model Routing

AI Architecture Hub

Mar 15, 2026 · Artificial Intelligence

How OpenClaw Solves Long‑Task Context Challenges for AI Agents

This article analyses the real‑world pain points of long‑running AI agents, breaks down OpenClaw’s core concepts, explains its three‑layer context‑compression pipeline, presents four key engineering decisions, shares six practical techniques with essential parameters, and compares OpenClaw to competing approaches.

AI AgentsLLM engineeringOpenClaw

0 likes · 17 min read

How OpenClaw Solves Long‑Task Context Challenges for AI Agents

prompt compression

Prompt Compression Creates a New LLM Vulnerability: HKUST’s Black‑Box Attack Framework COMA (ASE 2026)

10 Open‑Source Tools Cutting AI Agent Costs Ten‑Fold: Prompt Compression, Memory Management, Model Routing

How OpenClaw Solves Long‑Task Context Challenges for AI Agents

Prompt Compression Creates a New LLM Vulnerability: HKUST’s Black‑Box Attack Framework COMA (ASE 2026)