# Relatório Semanal de Survey: Software Aging & Rejuvenation em Edge LLMs
**Data:** 2026-10-29 | **Doutorando:** Magnus Alencar da Cruz (CISUC/DEI - UC)

## 1. Resumo Executivo da Semana
- **Artigos novos detetados:** 9
- **Artigos na interseção direta (Aging + Energy):** 0
- **Research Questions (RQs) ativas no banco de tese:** 7

## 2. Top Artigos Recentes Classificados nos Eixos da Tese
| CiteKey Sugerida | Título | Ano / Fonte | Horizon | Aging | Energy | Pilares (A1–A4) |
|---|---|---|---|---|---|---|
| `santos2026software` | Software Aging in LLM-Generated Applications: Runtime Evidence, Static Analysis, and Human-Written Comparisons (http://arxiv.org/abs/2608.26391v2) | 2026 (arXiv) | long | ✓ | --- | A1, A2 |
| `cotroneo2026characterizing` | Characterizing Software Aging in GPU-Based LLM Serving Systems (http://arxiv.org/abs/2606.11916v1) | 2026 (arXiv) | long | ✓ | --- | A1, A2, A3, A4 |
| `kim2026diagnosing` | Diagnosing and Mitigating Long-Session Degradation in Full-Duplex Speech Models (http://arxiv.org/abs/2610.34991v2) | 2026 (arXiv) | unknown | ✓ | --- | A1, A2 |
| `santos2025investigating` | Investigating Software Aging in LLM-Generated Software Systems (http://arxiv.org/abs/2510.24188v1) | 2025 (arXiv) | long | ✓ | --- | A1, A2 |
| `bai2023understanding` | Understanding Container-based Services under Software Aging: Dependability and Performance Views (http://arxiv.org/abs/2308.12784v1) | 2023 (arXiv) | long | ✓ | --- | A1, A2, A3 |
| `zhang2026bellowskv` | BellowsKV: One Latent for Many Layers, Expanded on Demand (http://arxiv.org/abs/2610.35023v1) | 2026 (arXiv) | unknown | --- | --- | A2 |
| `tsur2026rift` | RIFT: KV Cache Compression for Draft Models with Complementary Compressibility Training (http://arxiv.org/abs/2610.31098v1) | 2026 (arXiv) | short | --- | --- | A2 |
| `kim2026moezip` | MoEZip: Routing-Aware KV Cache Compression for Sparse Mixture-of-Experts LLMs (http://arxiv.org/abs/2610.30206v1) | 2026 (arXiv) | short | --- | --- | A2 |
| `wang2026tidekv` | TideKV: Delayed KV Eviction via Layer-Wise Chunked Prefill for Memory-Efficient Long-Context LLM Inference (http://arxiv.org/abs/2610.24499v1) | 2026 (arXiv) | unknown | --- | --- | A2 |

## 3. Alimentação de Research Questions (RQs) para os Papers 2, 3 e 4
- **RQ1-SEPARABILITY [A1 — paper2-aging-position / paper3-mechanism]**: How can progressive software aging in long-running LLM inference runtimes (e.g., Ollama / llama.cpp) be statistically isolated from thermal throttling and DVFS governor drift under variable arrival workloads?
  - *Hipótese*: Under fixed hardware frequency caps (e.g., 2.5 GHz) that eliminate turbo thermal saturation, any residual monotonic drift in per-token latency or RSS memory over >24h is attributable to runtime/OS state accumulation rather than thermal decay.
- **RQ2-LAYER-LOCALIZATION [A2 — paper3-mechanism]**: Which intervention (container/process restart, KV-cache flush, or OS page-cache drop via /proc/sys/vm/drop_caches) restores throughput and Joules-per-token efficiency without requiring a full node reboot?
  - *Hipótese*: In MoE and dense GGUF models on CPU-only edge nodes, memory allocator fragmentation and OS page-cache eviction pressure account for the majority of non-thermal throughput drift, recoverable via lightweight process restart without OS reboot.
- **RQ3-JOULE-REJUVENATION [A3 — paper4-framework]**: When is the energy and carbon cost of a rejuvenation action (e.g., reloading a 4.7 GB–8.9 GB GGUF model into RAM) amortized by the post-rejuvenation reduction in Joules per token?
  - *Hipótese*: Energy-aware rejuvenation is only net-positive in Joules when the cumulative throughput degradation slope exceeds E_rejuv / (P_active * T_horizon); under high-carbon grid hours, deferring rejuvenation to low-carbon windows minimizes gCO2eq.
- **RQ4-VERIFIABLE-PROTOCOL [A4 — paper2-aging-position / paper4-framework]**: What minimal continuous out-of-band telemetry invariants are required to certify that a multi-day edge AI experiment actually maintained its declared hardware and workload state?
  - *Hipótese*: Boundary-only configuration checks fail silently in >15% of multi-day edge campaigns (as demonstrated by the two uncapped 2.5 GHz runs and the 40.1h power telemetry drop in Paper 1); continuous in-band + out-of-band cross-auditing detects 100% of silent cap violations and sensor dropouts.
- **RQ5-WORKLOAD-NONSTATIONARITY [A1 — paper3-mechanism]**: Does bursty/diurnal prompt arrival accelerate KV-cache allocator fragmentation compared to closed-loop saturation at equal total token volume?
  - *Hipótese*: Variable prompt lengths and bursty inter-arrival times trigger frequent KV-cache reallocations, increasing heap fragmentation compared to uniform saturation.
- **RQ6-MOE-EXPERT-HOTSPOTS [A2 — paper3-mechanism]**: Do Mixture-of-Experts (MoE) models (e.g., DeepSeek-v2 Lite) exhibit different page-cache and RSS aging trajectories than dense models due to sparse expert routing?
  - *Hipótese*: Sparse activation across experts creates non-uniform page access patterns that interact differently with kernel page-cache eviction over multi-day runs.
- **RQ7-CARBON-AWARE-REJUVENATION-WINDOW [A3 — paper4-framework]**: Can rejuvenation actions (process restart / cold model reload) be co-scheduled with low-carbon grid windows (e.g., solar midday in PT/ES) to reduce net rejuvenation carbon cost by >40%?
  - *Hipótese*: Aligning proactive rejuvenation with diurnal grid carbon troughs minimizes the gCO2eq penalty of model reload spikes while preventing late-stage aging degradation.