Proactive memory for long-horizon agents
A paper dated July 10, 2026 presents a separate memory agent that maintains structured information and decides when to offer reminders to an action agent.
Read articleKnowledge you can apply
Radar
Daily bookmarks: relevant news, facts and discoveries.
Can metacognition lower the cost of LLM reasoning?
An article investigates whether models can balance accuracy, context size, compute cost, and latency without relying on long reasoning chains.
Read articleQuadRF tracks drones and detects Wi-Fi
Published on July 10, 2026, Jeff Geerling’s account presents QuadRF, a phased-array radio built with a Raspberry Pi 5 and an FPGA board. It uses signal processing and beamforming to track drones and detect Wi-Fi through walls.
Read articleHierarchical search agents: delegation and execution
An article published on July 9, 2026 examines how to distribute model capacity across delegation and execution roles in hierarchical search agents. The post identifies decomposition capacity as the main performance bottleneck.
Read articleTwo-core GPU implemented on a US$30 FPGA
Published on July 9, 2026, the project describes a two-core GPU on a US$30 FPGA, with a 16-bit ISA, assembler, J++ language, compiler, and AI inference at 81 MHz.
Read articleStudy compares costs and quality in agent orchestration
Published July 9, 2026, the study evaluates 22 tasks across six models, changing only the orchestration layer. It reports lower costs, token use, and runtime, with equivalent task-completion quality.
Read articleAsynchronous RL rollouts for agentic training
Published on July 9, 2026, the article discusses asynchronous RL for language-model post-training, with updates as rollouts arrive. It cites clipping adjustments in GLM 5.2 PPO and also points to VAPO.
Read articleInference caching: evaluate performance and isolation
Efficient memory can improve service capacity. The design must also prevent one session's context from appearing in another session.
Read articleCMDR assesses multimodal document retrieval across pages
The article presents CMDR and CMDR-Bench for retrieving relevant pages from multimodal documents when queries depend on context spanning multiple pages.
Read articleDiffusion language models: techniques in focus
A Kuleshov Group post presents research on diffusion language models, covering masked diffusion, iterative refinement, post-training, and variable-length generation.
Read articleFrom nvcc to warps: tracing a CUDA kernel
Published on July 8, 2026, the article follows a vector-sum kernel from compilation with nvcc to execution by GPU warps.
Read articleOn-policy distillation routes supervision per token
A paper describes a method that dynamically selects, token by token, between supervision based on a teacher and on the model itself.
Read articleColBERT: lightweight vector compression fine-tuning
A paper published on July 8, 2026 presents pooling-aware fine-tuning and k-means to reduce token vectors in ColBERT documents, claiming to preserve accuracy.
Read articleNapMem proposes active navigation of memory
An article published on July 8, 2026 presents NapMem, a framework that organizes a user's history in a linked memory pyramid with multiple granularities.
Read articleNapMem explores long-term memory for agents
Published on July 8, 2026, NapMem organizes user history into memory layers and trains an agent to choose which layer to inspect. The proposal contrasts with relying only on evidence preselected by a retriever.
Read articleWhat theory reveals about MaxSim
Published on July 8, 2026, the article examines MaxSim’s representational power and reports that it can exactly reproduce inner products between nonnegative k-sparse vectors.
Read articleQwen 3.5 and Nemotron 3 use different hybrid architectures
Published on July 8, 2026, the post compares two hybrid architectural approaches and relates them to the convergent evolution of linear attention and state-space models.
Read articleRidgeline: a roofline profiler for LLM inference
Ridgeline is a small profiler built with PyTorch to help engineers analyze LLM inference workloads using a roofline model.
Read articleSearchEyes trains search agents in simulated worlds
Published on July 8, 2026, the summary presents SearchEyes, an approach that uses a typed knowledge graph as the basis for a simulated search world to train multimodal agents.
Read articleBrowserBC turns browsing traces into skills for agents
The approach converts human browsing traces into natural-language skill cards that agents can retrieve and combine to navigate unfamiliar websites.
Read articleRota Nacional
Bring privacy into your workflow.
30 days, no card, with a starting quota. After that, Pix credit from R$ 10,00.