arXiv AI
Jun 16
Frontier: Towards Comprehensive and Accurate LLM Inference Simulation
arXiv:2605. 21312v2 Announce Type: replace-cross Abstract: Modern LLM serving is no longer homogeneous or monolithic.
From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix
Related stories
arXiv AI
Jun 3
Synthesize and Reward -- Reinforcement Learning for Multi-Step Tool Use in Live Environments
arXiv:2606. 03892v1 Announce Type: cross Abstract: Training LLMs to orchestrate multi-step tool calls is held back by three coupled obstacles: realistic stateful execution environments are costly to build, synthetic training queries are often detached from the server's actual state (so the generated tool calls fail to execute), and recall-based RL rewards incentivize verbose tool-calling patterns.
arXiv AI
Jun 4
EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms
arXiv:2606. 04145v1 Announce Type: cross Abstract: Cloud LLM fine-tuning platforms increasingly serve RLHF workloads, where a learned reward model is optimized as a proxy for human quality.
arXiv Machine Learning
2d ago
BASE: Batch-Aware Selection of Experts Using Predicted Removal Error for Efficient MoE Decoding
arXiv:2609.36222v1 Announce Type: new Abstract: Large language models are increasingly expensive to serve. In large-scale serving systems, autoregressive decoding is often bottlenecked by transferrin...
arXiv AI
Sep 11
Why Sample What You Can Enumerate? Exact Policy Optimization for Genomic Tool Selection
The paper critiques the common reinforcement‑learning approach of sampling tool subsets when the full set of tools is enumerable, showing that sampling leads to degraded policy estimates and increased reward sparsity in genomic reasoning tasks. It proposes Full‑Group Policy Optimization (FGPO), which evaluates every tool subset and precomputes rewards in a table, thereby eliminating the need for frozen‑reasoner calls during training. Experiments across five frozen reasoners and three genomic benchmarks demonstrate that FGPO consistently outperforms GRPO, improving average scores by 6.75 points and reducing the number of invoked tools per question.
arXiv AI
Jun 2
Beyond Task-Agnostic: Task-Aware Grouping for Communication-Efficient Multi-Task MoE Inference
arXiv:2606. 01007v1 Announce Type: cross Abstract: Sparsely activated Mixture-of-Experts (MoE) models scale capacity via conditional computation, but distributed inference suffers from cross-GPU expert communication and routing-induced load imbalance.
arXiv AI
Jun 4
Not All Errors Are Equal: Consequence-Aware Reasoning Compute Allocation
arXiv:2606. 04402v1 Announce Type: new Abstract: Modern reasoning models can allocate different amounts of test-time computation, such as thinking tokens, model calls, or compute budget, to different tasks.
arXiv AI
Jul 17
Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Optimization Agent
arXiv:2607. 14541v1 Announce Type: new Abstract: Existing GPU kernel generation benchmarks draw problems from synthetic or curated sources that diverge from deployed workloads.
Hugging Face Trending Papers
Sep 9
Why Sample What You Can Enumerate? Exact Policy Optimization for Genomic Tool Selection
Reinforcement learning over a frozen reasoner has become a common recipe for teaching a policy which external tools to invoke. We show that this recipe becomes structurally mismatched in specialist sc...
arXiv Machine Learning
Aug 3
DeltaServe: Host-Agnostic Co-Serving of Inference and Fine-Tuning for LLMs
arXiv:2607. 28848v1 Announce Type: cross Abstract: LLM serving systems are provisioned for peak load to meet strict latency targets, leaving substantial GPU compute idle whenever traffic falls below peak.
arXiv AI
Sep 15
Learning to Solve Hard Problems in RL for LLMs by Never Giving Up
arXiv:2609.13443v1 Announce Type: cross Abstract: We demonstrate that training LLMs with RL does not improve performance equally across a dataset. RL shows large improvements on easy problems that an...
arXiv AI
Jun 3
Libra: Efficient Resource Management for Agentic RL Post-Training
arXiv:2606. 03077v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a standard post-training paradigm for large language models (LLMs), extending beyond preference alignment to complex reasoning and multi-turn agentic behaviors.