TrawMem organizes agent memory by task role
On LoCoMo and MemGallery, authors report macro-F1 gains of 2.23–3.14 points and fewer context tokens than compared memory systems.
40
AI model
DeepSeek-V4-Flash
- Mentions · 7d0
- Mentions · 30d2
- All mentions10
- First seenSep 4, 2026
- Last mentioned15d ago
Timeline
10 articles · newest firstCoding-agent harnesses cost more without better benchmark scores
Harness swaps changed outcomes about as often as reruns, while system prompts made some tasks cost up to three times more.
46
ARTEX AI Pentesting Tool Used in Data Theft Attacks on South Korean Financial Firms
A suspected Chinese operator used the ARTEX AI pentest tool to steal data from South Korean financial firms.
76
FlowState keeps execution state as memory for long-horizon agents
Against a full-context DeepSeek-V4-Flash baseline, authors report higher pass rates and about 40% fewer tokens.
36
Automated Extraction of Records of Processing Activities (RoPA) Using Hybrid RAG and Locally Deployed Large Language Models
Researchers built RoPA Manager to extract Vietnam data-protection records using hybrid RAG and local LLMs.
38
DeepSeek-v4.1 Flash: Pushing the Limits of KV Cache Compression
DeepSeek-V4.1 Flash is a 552B-parameter multimodal MoE model with 1M-token context achieving 4x KV cache compression for long-horizon agent workloads.
74
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
DeepSeek releases V4.1-Flash, a 552B-parameter multimodal MoE with 1M-token context and 890-byte-per-token KV cache for cheaper agentic workloads; weights on Hugging Face.
84
The Self-Expanding Stolen Inference Supply Chain: An AI Agent Harvesting and Re-Serving LLM Access, (Fri, Sep 11th)
An autonomous coding agent harvested LLM API access from poorly secured gateways and aggregated stolen inference capacity behind a self-hosted gateway
68
DeepSeek AI Released DeepSeek-V4.1-Flash with 1M Context, FP4 KV Cache, and Cross-Layer Attention Reuse
DeepSeek released open-weight V4.1-Flash, a 552B MoE model with 1M context and FP4 KV cache, beating Opus-5 and GPT-5.6 Sol on agent benchmarks.
80
How Does mHC Use Its Residual Streams? Selective Routing and Near-Identity Mixing
Analysis of DeepSeek-V4-Flash shows four-stream mHC residual blocks use only about two streams effectively, with late-layer mixing providing little benefit.
42
Appears with
- DeepSeekvendor · 4
- DeepSeek-V4.1-Flashai model · 3
- DeepSeekorganization · 2
- GPT-5.6ai model · 2
- glm-5.3ai model · 2
- ARTEXproduct · 1
- vLLMproduct · 1
- Grok 4.6ai model · 1
- Zhipu AIorganization · 1
- DeepSeek v4.1-flashai model · 1
- OpenCodeproduct · 1
- claude-opus-5ai model · 1
- Hugging Faceorganization · 1
- Claude Opus 4.6ai model · 1
- Z.aivendor · 1
- gpt-5.6-solai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.