Live feed

github.com · 2026-10-28 · Ranked: agent match · community signal · fresh 0.99 · score 3.14 · Context

Moonfold: Coding tasks that survive agent usage limits

arxiv.org · 2026-10-27 · Ranked: agent + eval match · research watch · fresh 0.86 · score 2.99

Beyond the Evidence Coherence Trap: Agent-Driven Evidence Selection for Temporally Disordered Fake News Detection

Fake news undermines public trust and the integrity of online information ecosystems. Temporally disordered fake news is especially elusive because it rearranges factual events into a false chronology. Individual even... Context & related coverage →

arxiv.org · 2026-10-27 · Ranked: agentic + eval match · research watch · fresh 0.83 · score 2.96

RouteDRAG: Learning to Route and Control Agentic Execution for Multimodal Document RAG

Web-based applications increasingly rely on understanding long multimodal documents, where answering questions often requires combining information across pages, tables, and figures. Agentic retrieval-augmented genera... Context & related coverage →

arxiv.org · 2026-10-27 · Ranked: agentic + eval match · research watch · fresh 0.91 · score 2.86

Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness

We introduce Heads of Security (HoS), a prompt injection defense that enforces instruction-data separation via a small set of learned per-head attention gates. HoS learns how each head should redistribute attention be... Context & related coverage →

arxiv.org · 2026-10-27 · Ranked: evaluation match · research watch · fresh 0.89 · score 2.84

Coverage Under Contradiction: A Benchmark for Negation-Aware Retrieval

Coverage-evaluation benchmarks quantify whether retrieved evidence covers the different pieces of information needed to satisfy an information need. Existing benchmarks mostly consider factual claims that may already... Context & related coverage →

arxiv.org · 2026-10-27 · Ranked: research watch · fresh 0.90 · score 2.69

CRISP: Co-designing Pruning and Scheduling for Efficient MoE Inference on Edge Servers

Mixture-of-Experts (MoE) inference on memory-constrained edge platforms is often dominated by expert-weight movement rather than computation. Although each token activates only a small subset of experts, routing is in... Context & related coverage →

hackerscad.com · 2026-10-28 · Ranked: agent match · community signal · fresh 0.98 · score 2.68 · Context

Show HN: Hackerscad – Code-first CAD with MCP server for AI agents

itsfoss.com · 2026-10-28 · Ranked: community signal · fresh 0.98 · score 2.65 · Context

Rocky Linux Creator Built a New "Not Linux" Kernel in 11 Days Using AI