arXiv AI
23h ago
Beyond the Trace: Coupling an Interpretable Reasoning-State Readout to Native MoE Routing
arXiv:2608. 17638v1 Announce Type: new Abstract: What a reasoning model writes is only a partial record of the process that produces it.
Beyond the Trace: Coupling an Interpretable Reasoning-State Readout to Native MoE Routing
What a reasoning model writes is only a partial record of the process that produces it. We introduce a two-level internal readout for mixture-of-experts reasoning.
Related stories
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.
arXiv AI
Jun 6
ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces
arXiv:2606. 05402v1 Announce Type: cross Abstract: Large reasoning models (LRMs) produce reasoning traces with non-linear structures, such as backtracking and self-correction, that complicate the evaluation and monitoring of the reasoning process.
Hugging Face Trending Papers
Jul 27
DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference
Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory. We target latency-critical single-user settings where routed experts are staged on demand from CPU memory to a GPU or from Flash to a mobile NPU.
arXiv AI
6d ago
Moxia: A Trust-First Neuro-Symbolic Execution Architecture for Self-Explaining Mathematical Reasoning
arXiv:2606. 00671v3 Announce Type: replace Abstract: We present Moxia (formerly AXIOM), a trust-first neuro-symbolic architecture for self-explaining mathematical reasoning over natural-language input.
arXiv Machine Learning
1d ago
Every Expert Counts: ExactMoE for Memory-Efficient W4A16 Inference
arXiv:2608. 15383v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) language models reduce arithmetic by activating only a small subset of experts per token, yet deployment still requires storing and moving the full expert bank.
arXiv AI
Aug 11
ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention
arXiv:2603. 22016v3 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) often reach a correct solution before their long Chain-of-Thought trace ends, yet continue with redundant verification, repeated attempts, or unnecessary exploration that wastes computation and can even overturn the correct answer.
arXiv AI
Jun 9
Why Limit the Residual Stream to Layers and Not Tokens? Persistent Memory for Continuous Latent Reasoning
arXiv:2606. 07720v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable reasoning abilities on mathematical and multi-hop planning tasks.
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.
arXiv AI
Jul 28
DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference
arXiv:2607. 24434v1 Announce Type: cross Abstract: Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory.
arXiv AI
Jul 28
LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models
arXiv:2411. 00918v5 Announce Type: replace-cross Abstract: Mixture of experts (MoE) architectures have become a cornerstone for scaling up and are a key component in most large language models such as GPT-OSS, DeepSeek-V3, Llama-4, and Gemini-2.
arXiv AI
Jul 28
DeepLook: Deeper Thinking with Lookahead
arXiv:2607. 22602v1 Announce Type: new Abstract: Inference-time scaling has emerged as a powerful paradigm for improving large language model reasoning, often delivering larger gains on difficult reasoning tasks than parameter scaling alone.