Flide is an inference engine that accelerates decision models by decoupling the logical tree of a decision request from its physical execution within a single flattened token stream. It uses ForkAttention to navigate request dependencies with GPU-resident indices across standard attention and recurrent Gated DeltaNet layers, ensuring exact arithmetic equivalence to isolated forward passes. Evaluations show Flide can answer queries up to 9.5× faster than vLLM and SGLang while maintaining close alignment to a float32 reference in total variation distance.
arXiv:2608. 08020v1 Announce Type: new Abstract: Test-time compute scaling is a primary driver of performance in large reasoning models (LRMs), but extreme inefficiency bounds current approaches, shifting the critical question from \emph{how much} compute to spend, to \emph{where} to allocate it.
arXiv:2604.18616v2 Announce Type: replace-cross Abstract: LLM coding agents can generate correct GPU kernels, but their performance still trails expert libraries. Reaching peak throughput requires co...
The paper introduces Gated-Memory Routing, a method for efficient collaboration in multi‑agent large language model systems. It uses a learned execution memory with write and retrieval gates to keep only non‑redundant reasoning steps, and an adaptive halting controller to stop execution when enough evidence is gathered. Experiments on five reasoning and code‑generation benchmarks show the approach achieves higher accuracy and reduces inference cost by 31.9% compared to the strongest baseline.
arXiv:2608. 01651v1 Announce Type: cross Abstract: Hybrid-attention large language models combine full attention with recurrent linear attention to reduce long-context inference costs, yet their autoregressive decoding remains memory-bound.
LoongSage is a lightweight, fully asynchronous reinforcement learning framework designed for large language models that perform agentic tasks. It integrates with Megatron for distributed training and SGLang for high‑throughput inference, centralizing orchestration in a single controller and using Ray actors for GPU components. The framework introduces AgentFlow for unified execution of white‑box and black‑box agents, sliding‑window strategies to limit trajectory staleness, TransferMesh for efficient weight synchronization, and a memory‑efficient Teacher Manager that supports multi‑teacher on‑policy distillation. Experiments across four training runs show steady reward improvement, controlled train‑inference gaps, and sustained hardware utilization by eliminating synchronous idle periods.
arXiv:2608.21614v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting improves LLM reasoning by decomposing complex problems into intermediate steps, but its sequential nature increases de...
The paper introduces SCX Router, a lightweight GLiClass-based model selector that assigns suitability scores to inference-time language models without autoregressive generation. It uses a 0.6B-parameter Qwen3 decoder with a shallow bidirectional scorer, preserving a text-only key–value cache across sessions and predicting task attributes such as type, difficulty, and expected output length. The authors build a comprehensive task ontology with 23 families, 115 types, and 1,173 synthetic examples, generating 150,000 verifier-scored tasks to train the router, which outperforms baseline models on LiveBench subsets with a top‑1 score of 0.707 versus 0.696 for the strongest fixed model.
arXiv:2603. 03589v3 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) transform how machine learning (ML) pipelines are developed and evaluated.
arXiv:2607. 11399v1 Announce Type: cross Abstract: Large language model agents are increasingly executed not by a single model call, but by an execution harness that manages observation, context, control, action, state, and verification.
SCOPE compiles natural‑language policies into neurosymbolic predicate programs that combine small neural models, deterministic extractors, and logical composition. The system is jointly optimized with adversarially generated counterexamples, achieving higher accuracy than prompt‑optimization, task‑decomposition, and workflow‑generation baselines on real‑world policy benchmarks. Programs trained with the weakest executor transfer to other models, enabling deployment on inexpensive models with stable, interpretable predictions.
arXiv:2606. 02963v1 Announce Type: new Abstract: Production inference increasingly targets a heterogeneous mix of accelerators.
arXiv:2607. 01831v1 Announce Type: cross Abstract: Long-context inference is increasingly common in large language model (LLM) serving, driven by retrieval-augmented generation and agentic systems.