arXiv Machine Learning June 17, 2026 By Kaviru Hapuarachchi

When the Next Step Is Not One Step: Distribution-Aware Execution Modeling for Concurrent Go Programs

Read the original on arXiv Machine Learning →

arXiv:2606. 17508v1 Announce Type: new Abstract: Training a model to predict the next step in a concurrent program is harder than it looks: two runs of the same program from the same trace prefix can produce different next events, both valid, because the scheduler is nondeterministic.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

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.

By Guilin Zhang, Chuanyi Sun, Shahryar Sarkani, John M. Fossaceca

llms reinforcement-learning fine-tuning

arXiv AI

Jul 7

SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference

arXiv:2607. 03333v1 Announce Type: cross Abstract: LLM agents are becoming a common interface for research, coding, and question answering, yet their Thought-Action-Observation loop is often serial: the model reasons, emits a tool call, then idles the GPU until the result returns.

By Huajun Bai, Weiwei Lv, Huichuan Zheng, Youyou Lu, Jiwu Shu

llms agents nlp benchmarks

arXiv Machine Learning

Aug 11

When Does Trace-Driven Evaluation Mislead MoE Expert Caching? Replay Semantics, Workload Contamination, and Operating Regimes

arXiv:2608. 07911v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have outgrown accelerator memory, and offloading expert weights to host memory is now standard.

By Yu Zhang

arXiv AI

Aug 5

TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows

arXiv:2608. 02680v1 Announce Type: cross Abstract: Tool-using language-model agents repeatedly rediscover procedures they have already executed, producing traces that mix reusable structure with retries, exploration, accidental ordering, and repeated lookups.

By Salma El Yadouni (EPFL), Guanyi Li (Binome Technologies)

llms agents benchmarks

arXiv AI

1d ago

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

arXiv:2608. 15089v1 Announce Type: new Abstract: Long-horizon agents can fail even when their underlying models can solve the constituent steps.

By Ziheng Qin, Yaxin Lu, Zhangyang Atlas Wang, Kai Wang

llms agents

arXiv Machine Learning

Aug 5

When RL Meets Adaptive Speculative Training: A Unified Training-Serving System

arXiv:2602. 06932v5 Announce Type: replace Abstract: Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone offline modeling problem.

By Junxiong Wang, Fengxiang Bie, Jisen Li, Zhongzhu Zhou, Zelei Shao, Yubo Wang, Yinghui Liu, Qingyang Wu, Avner May, Sri Yanamandra, Ce Zhang, Tri Dao, Percy Liang, Ben Athiwaratkun, Shuaiwen Leon Song, Chenfeng Xu, Xiaoxia Wu

llms reinforcement-learning

Related stories

EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms

SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference

When Does Trace-Driven Evaluation Mislead MoE Expert Caching? Replay Semantics, Workload Contamination, and Operating Regimes

TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

When RL Meets Adaptive Speculative Training: A Unified Training-Serving System