安全规则与日志争抢上下文，压缩时规则一字之差即失效，长跑AI智能体记忆悬崖的实证研究
arXiv:2608.22752v1 Announce Type: new Abstract: A safety rule and an episodic log compete for the same tokens in an AI agent's context. When the budge…
MCP上下文被工具定义吃光？实测91% token压缩方案，50KB CLI解决五大痛点，AI Agent开发必看
5 MCP Pain Points Every Developer Hits (And How a 50KB CLI Fixes Them) I've been using MCP servers with Claude Code, Cursor, and Codex for months. Eve…
当上下文被压缩，模型还能守住约束吗？这篇论文系统评估“侧约束损失”，揭示压缩带来的隐藏风险。
arXiv:2608.11242v1 Announce Type: cross Abstract: When the context window is under pressure, LLM systems compact prior context to continue ongoing tas…
大模型上下文压缩迎来首个统一理论框架，从数学层面揭示信息保留与压缩比的最优平衡，值得关注。
arXiv:2608.01326v1 Announce Type: cross Abstract: Large Language Models (LLMs) have a bounded context window. The context window is the maximum input …
不到1MB的C++重写OpenAI Codex，支持交互终端与自动上下文压缩，轻量级编程代理新选择。
Article URL: https://github.com/paoloanzn/microcodex Comments URL: https://news.ycombinator.com/item?id=49147842 Points: 11 # Comments: 3
探讨Claude Code上下文压缩的机制与细节保留，技术干货值得一试。
What happens when we do compress the context in claude code? How does the reduce the context with out loosing the details? Comments URL: https://news.…
真实数据揭示LLM编码代理90%时间浪费在重读上下文，手把手教你控制token成本
I have been using LLMs & Coding Agent since early 2024. A large problem with Coding Agents & LLMs in general is context compression. To give you some …
Edgee推出Compressor V2，三层次压缩策略将LLM Agent成本砍半，性能与效率兼得。
Article URL: https://www.edgee.ai/blog/posts/introducing-compressor-v2-three-compression-layers-measured-end-to-end-for-a-50-cost-reduction Comments U…
揭示LLM长对话中上下文压缩悄然抹除安全护栏的隐患，值得AI安全领域关注。
arXiv:2606.22528v1 Announce Type: new Abstract: Modern LLM agents increasingly rely on context compaction, summarization, or eviction to keep long-run…
给AI Agent的上下文做瘦身：JSON数据最高省95%token，代码场景省15-20%，还支持代理/MCP接入，性能可观。
Article URL: https://github.com/headroomlabs-ai/headroom Comments URL: https://news.ycombinator.com/item?id=48627072 Points: 1 # Comments: 0
开源自托管AI Agent OS，ArkDistill压缩噪点输出60-90%，大幅节省上下文空间！
Article URL: https://github.com/agentark-ai/AgentArk Comments URL: https://news.ycombinator.com/item?id=48606186 Points: 3 # Comments: 0
零配置AI agent上下文压缩工具，从56K token骤降至1.9K，自动学习你的编程风格，兼容任意agent。
Article URL: https://github.com/dvcoolarun/taste-ai Comments URL: https://news.ycombinator.com/item?id=48608707 Points: 1 # Comments: 0
本地代理tokdiet通过智能上下文优化，在不牺牲回答质量的前提下，将LLM token开销削减高达70%，实测基准验证效果。
Article URL: https://github.com/agiwhitelist/tokdiet Comments URL: https://news.ycombinator.com/item?id=48563156 Points: 1 # Comments: 1
比压缩算法好2倍：Lore用智能记忆管理让AI编码代理告别68分钟/天的重复解释，总召回率提升至2.6倍。
Article URL: https://withlore.ai/ Comments URL: https://news.ycombinator.com/item?id=48464573 Points: 4 # Comments: 0
实时压缩代码上下文，降低LLM API成本50-80%，可直接嵌入的代理工具。
Article URL: https://github.com/borhen68/TokenTamer Comments URL: https://news.ycombinator.com/item?id=48458633 Points: 1 # Comments: 1
反事实推理优化LLM Agent记忆管理，创新性地解决工具使用中的上下文选择与压缩难题。
arXiv:2606.08151v1 Announce Type: new Abstract: Tool-using LLM agents often fail not because relevant text is absent, but because decisive evidence is…
最新论文提出ACON方法，优化长时域LLM代理的上下文压缩，显著提升推理效率与准确性。
arXiv:2510.00615v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as agents in dynamic real-world environment…
提出思考即压缩的观点，把大模型推理能力重新定义为上下文压缩机制，视角极为新颖
arXiv:2605.28713v1 Announce Type: new Abstract: Context compression aims to shorten long context inputs with minimal information loss for LLM inferenc…
针对长时LLM Agent的上下文溢出问题，提出并行压缩方法，减少数十秒推理阻塞。
arXiv:2605.23296v1 Announce Type: new Abstract: Long-horizon LLM agents accumulate growing conversation histories that eventually exceed the model's c…
提出可验证的LLM上下文压缩形式化框架，压缩同时保持承诺完整性，AI安全新思路。
arXiv:2605.17304v1 Announce Type: new Abstract: LLM context is not just tokens; it is a set of commitments. Long-running conversations accumulate goal…