Weekly Recap

DataMagic achieves over 95% success rate and an 83% quality improvement in data video generation by declaratively orchestrating multi-agent scene creation, surpassing even state-of-the-art LLMs.

Blackwell GPUs' FP4 Tensor Cores unlock 2.81x output throughput for long-context LLMs by strategically using mixed precision and rank-one smoothing, bypassing attention bottlenecks.

Existing SFT reweighting methods fail to reverse harmful learned features; a new entropy-guided approach enables precise suppression, reversal, and extrapolation of pretrained knowledge.

Coding agents can now achieve up to 15% higher task completion rates by treating feedback as a persistent note that's followed until resolved, not just a one-off evaluation.

Personal GUI agents waste most of their retrieved history; this framework activates experience only when it's actually applicable, boosting performance and efficiency.

DataMagic achieves over 95% success rate and an 83% quality improvement in data video generation by declaratively orchestrating multi-agent scene creation, surpassing even state-of-the-art LLMs.

Blackwell GPUs' FP4 Tensor Cores unlock 2.81x output throughput for long-context LLMs by strategically using mixed precision and rank-one smoothing, bypassing attention bottlenecks.

Existing SFT reweighting methods fail to reverse harmful learned features; a new entropy-guided approach enables precise suppression, reversal, and extrapolation of pretrained knowledge.

Coding agents can now achieve up to 15% higher task completion rates by treating feedback as a persistent note that's followed until resolved, not just a one-off evaluation.

Personal GUI agents waste most of their retrieved history; this framework activates experience only when it's actually applicable, boosting performance and efficiency.

Frontier LLMs struggle to replicate expert consensus in complex, longitudinal cancer treatment discussions, scoring below expert equivalence on a new real-world benchmark.

HeteroFold unlocks $10.7\times$ faster cross-family KV cache transfer for LLMs, eliminating receiver prefill and matching text-based communication performance.

Control accent strength in zero-shot TTS with a single model and inference-time weight, outperforming cascaded systems on out-of-domain accents without sacrificing speaker identity.

Agents can achieve up to 5.8% higher success rates by learning a reusable "experience tree" directly from data, bypassing LLM-generated skills and enabling true generalization.

ZooWork-ShopRanker, a family of e-commerce rerankers aligned to judge-labeled shopping preference, and ShopRank-Bench, a contamination-limited benchmark of ~10,000 private-traffic preference pairs in both text formats, tiered by how many judge families committed to each label.

Iterative intent denoising enables decentralized multi-agent pathfinding agents to coordinate complex joint actions, overcoming the limitations of one-shot sampling and achieving near-perfect task completion.

Latent communication can be compressed by 75% without accuracy loss by conditioning KV cache transmissions on receiver information needs.

AI systems can auto-evolve by learning from their own failures, achieving 20.5% better performance with 65.5% fewer rollouts than existing methods.

City-scale UAV navigation with satellite imagery reveals current VLN agents forget 40% of context after 379m, necessitating new memory architectures.

This work proposes SLCA-GRPO, a framework incorporating Segment-Locked Credit Assignment (SLCA), a framework incorporating Segment-Locked Credit Assignment (SLCA) that decouples advantage estimation at the structural segment level within a single group of rollouts, without requiring additional rollouts from intermediate states.

Enterprise AI agents can now generate valid, high-fidelity tabular data for training and evaluation without needing access to sensitive schemas or real systems, bypassing critical industry bottlenecks.