Papers arxiv:2605.06628 LiVeAction: a Lightweight, Versatile, and Asymmetric Neural Codec Design for Real-time Operation Published on May 7 Submitted by Dan Jacobellis on May 11 Authors: Dan Jacobellis , Abstract LiVeAction is a lightweight neural codec architecture that improves rate-distortion pe… …
… Our experiments reveal that: \circone code-specialised embeddings dominate code-to-code retrieval {sim}2{times} over general encoders , yet no single model wins all three tasks; \circtwo short keyword queries, the format closest to real developer search, collapse every model to near-zero nDCG@10; \… …
… However, most agent benchmarks still rely on synthetic sandboxes, short-horizon tasks, mock-service APIs, and final-answer checks, leaving open whether agents can complete realistic long-horizon work in the runtimes where they are deployed. …
… Overall, we show that provenance tracking for generated code can be made practical for real-world LLM systems. …
… View arXiv page View PDF GitHub 7 Add to collection Community Closed-loop auto research turns agent-written code, real experiments, and evaluator feedback into an autonomous feedback loop that develops non-trivial training recipes. the most interesting nugget here is how lineage feedback lets evalu… …
… AI-generated summary Vision-Language-Action VLA models aim to provide a single generalist controller for robots, but today's systems fall short on the criteria that matter for real-world deployment. …
… What really excites me is the cost optimization angle - automatic hardware matching means you're not overpaying for compute while still getting reasonable training times. …
… The following papers were recommended by the Semantic Scholar API AgentKernelArena: Generalization-Aware Benchmarking of GPU Kernel Optimization Agents 2026 FACT: Compositional Kernel Synthesis with a Three-Stage Agentic Workflow 2026 Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimizat… …
… We're really glad the perspective on many-shot CoT-ICL as in-context test-time learning was interesting to you. …
… By integrating Diffusion Posterior Sampling DPS with temporal Sampling-Aware Test-Time Adaptation TTA , we show that the dataset allows synthetic models to align with real-world statistics on-the-fly, transforming the intractable sim-to-real challenge into a tractable self-supervised task. …