Latest

Every published item, in order · 9845 items
Nov 3
PapersSelected14:29
AttentionIndex Speeds Learned Sparse Attention on GLM-5.3 and DeepSeek-V4-Flash

The method cuts indexer cost, which accounts for over half of prefill time at one million tokens, without the recall degradation that two-stage block approaches like HiSA suffer as context grows. Serving teams running long-context inference on models with learned sparse attention, such as GLM-5 or DeepSeek-V4, can use it to raise prefill throughput 1.3-1.8 times while preserving retrieval accuracy. Both target models come from Chinese labs, making it directly relevant to practitioners deploying these open-weight models.

arXiv: DeepSeek@Jeongmin Brian Park, Wen-mei HwuSource
PapersBuildersSelected14:29
J-PACT Detects Collusion Between LLM Agents via J-Space

Unsupervised detection matters because supervised probes need labelled collusion data that real deployments rarely have, so J-PACT lowers the barrier to auditing multi-agent systems. Teams running agent swarms — especially in finance, trading or messaging pipelines where hidden coordination is hard to spot — can use J-space signals as an oversight layer. The method worked across four open-weight model families, suggesting the collusion signature is not model-specific.

arXiv: DeepSeek@Marco Molinari, Gabriele BettineschiSource
PapersBuildersSelected14:23
Thoughtworks veterans stay wary of coding agents in production

The lesson is that 'it runs' and 'it is safe to run in production' are still far apart with agents, and guardrails — tests, contracts, architecture checks — matter more than raw code output. Engineering leads and platform teams evaluating agentic workflows should budget for harness-building and design feedback loops rather than measuring speed alone. The whiteboard-to-harness split offers a concrete template for how roles may shift, though Thoughtworks itself calls the story incomplete.

shao__meng@shao__mengSource
PapersBuildersMulti-sourceSelected14:19
Code Mode converges agent tool calling into a single exec tool

The shift changes how agent harnesses should be designed: instead of engineering tool schemas and prompts, expose typed functions and let the model orchestrate in code, which also cuts token costs from intermediate outputs. Builders of agent frameworks and MCP servers should consider adding exec-style sandboxes and outputSchema support. Typed JS/Python sandboxes beat bash for chaining MCP tools since models skip shell-escaping and CLI flag discovery.

Event
shao__meng@shao__mengSource
PapersBuildersMulti-sourceSelected14:19
DecisionRAG: Cornell paper replaces retrievers with a decision model over document trees

The interesting shift is that retrieval becomes a tree-traversal decision problem instead of an embedding-similarity problem, so latency scales with tree depth rather than corpus size, with billion-paragraph corpora theoretically needing around five decisions. Teams paying for a reranker stage, or struggling with weak first-stage recall on help centres and document corpora, can test the tree-plus-decision-model setup; on NQ a dense retrieval stage can optionally be mixed in to recover over-pruned evidence. It competes with Qwen3-Reranker-8B pipelines at lower cost.

Event
shao__meng@shao__mengSource
Tomorrow 08:00, the daily lands in your inboxTelegram channel or email. Same screening as this page, no ads.

Only the latest 2000 items are listed; for older ones see the daily archive