Here's how we find the best route for every user: → Our API queries all available liquidity sources & aggregation APIs → We simulate each option on our in-house infrastructure → Best route is automatically selected for the trade

new: i8 vectors f32: 4 bytes/dim i8: 1 byte/dim 4x fewer bytes → 75% lower storage and query costs + faster queries when embedded with a quantization-aware model (e.g. voyage-4-large) trained on i8 vectors, recall loss can be ~0! docs:

🔎 A paper that pinpoints the hidden reason RL training for search agents stalls partway. Title: Harness-G: A Graph-Structured Harness for Search Agents URL: ❓ Why does training collapse? 💡 It's "retrieval-equivalence collapse." The policy keeps generating differently-worded queries that fetch the same evidence, so same evidence → same answer → same reward, within-group advantages vanish, and the training signal dries up. ❓ How does Harness-G fix it? 💡 It stops free-form query generation and turns it into menu selection over a paragraph-sentence-entity graph built from the corpus. The policy picks action IDs, not strings. Being finite, verifiable, and previewable, it preserves diversity in what actually gets retrieved. ❓ What is the credit assignment (SNC)? 💡 A frozen answerer previews how much an action raises the gold-answer probability, scored against alternatives (frontier-relative). Non-myopic payoffs like "find the bridge entity first" propagate back through provenance edges (enablement). No extra rollouts needed. ❓ Does it work? 💡 Across six QA benchmarks it beats Graph-R1 by +10.74 at 1.5B and +3.98 at 3B, best at both scales, especially on multi-hop, with $0 API cost to build the graph. #SearchAgents# #ReinforcementLearning#

Notice of upcoming changes to CosmWasm: A new forum discussion is live asking for feedback on two Wasm updates on the Cosmos Hub: - Increase max contract size to 1.6MiB - Implement two additional Wasm gRPC queries Forum post link: