arXiv AI
Aug 17
PPAPlace: Differentiable Cross-Stage Objectives for Chip Placement Optimization
arXiv:2608. 13790v1 Announce Type: cross Abstract: Macro placement significantly affects a chip's post-route performance, power, and area (PPA).
CoEvoP&R: Co-Evolving Placement Objectives with Routing Feedback via Large Language Models
arXiv:2607. 17398v1 Announce Type: cross Abstract: Analytical placers rely on differentiable objective functions to guide placement, typically combining intermediate surrogate metrics such as half-perimeter wirelength (HPWL) and cell-density penalties.
Related stories
arXiv AI
Sep 21
PlaceReasoner-Beta: Reasoning-Driven Macro Placement and Benchmarking
arXiv:2609.21263v1 Announce Type: new Abstract: Automated macro placement remains a fundamental challenge in VLSI physical design. Despite decades of research, existing approaches predominantly optim...
arXiv Machine Learning
Jun 16
HyDRA: Hybrid Dynamic Routing Architecture for Heterogeneous LLM Pools
arXiv:2605. 17106v2 Announce Type: replace-cross Abstract: Production LLM deployments increasingly maintain heterogeneous model pools spanning order-of-magnitude cost differences.
arXiv AI
4d ago
TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing
arXiv:2605.18859v3 Announce Type: replace-cross Abstract: LLM routing matters most in long-horizon applications such as coding agents, deep research systems, and computer-use agents, where a single u...
arXiv AI
Jul 8
Think Before You Grid-Search: Floor-First Triage for LLM Serving
arXiv:2607. 05876v1 Announce Type: cross Abstract: LLM serving optimization typically benchmarks many configurations and reaches for heavy profilers when latency targets are missed.
arXiv AI
Aug 19
Beyond the Trace: Coupling an Interpretable Reasoning-State Readout to Native MoE Routing
The paper introduces a two‑level readout for mixture‑of‑experts reasoning models. First, it compresses the model’s internal reasoning states into a 64‑dimensional semantic frame (J64) that reveals process dynamics beyond the emitted trace. Second, it reconstructs this frame from native expert‑routing statistics (R64), achieving high correlation and preserving most predictive gains while enabling low‑overhead, test‑time decision making.
arXiv AI
Jul 20
Diagnosing Overhead in Dispatch Operations: Cross-architecture Observatory
arXiv:2605. 20982v2 Announce Type: replace-cross Abstract: AlltoAll dispatch is the dominant bottleneck of MoE expert parallelism, and the interconnect community has responded with four families of mitigations: predictive sample placement, adaptive expert relayout, hierarchical collectives, and EP-aware topology.
arXiv AI
Sep 7
ACE: Adaptive Calibration-Free Expert Skipping for MoE-based LLMs
ACE introduces a training‑free, calibration‑free framework for adaptive expert skipping in Mixture‑of‑Experts LLMs. It combines a Global Spectral Proxy that estimates global transformation capacity with a Router‑Conditioned Refinement that builds expert‑specific direction prototypes, enabling the model to skip low‑contribution experts while always keeping the top‑1 expert. Offline computation of expert statistics leaves only lightweight table lookups during inference, and experiments on three MoE‑based LLMs show ACE outperforms static and dynamic baselines, especially at high skipping ratios.
arXiv AI
Sep 10
Do Dynamic Routers Need Memory? HeRo: History-Aware Routing for Efficient LLM Inference
arXiv:2609.08189v1 Announce Type: new Abstract: Dynamic layer routing reduces the inference cost of Large Language Models (LLMs) by learning to skip layers for individual tokens. Existing methods, ho...
arXiv AI
Aug 24
Nexus: Depth-Adaptive KV-Cache Splicing and Retrieval-Decoupled Tool Routing for Agentic LLMs on Unified Memory
Nexus introduces a depth‑adaptive KV‑cache splicing and retrieval‑decoupled tool routing mechanism for agentic large language models that reduces the time‑to‑first‑token (TTFT) by decoupling tool routing from the expensive schema re‑encoding step. It uses an INT8 semantic lookaside buffer to select tools via retrieval and generates arguments from a compressed textual signature, maintaining about 89% routing accuracy even as the tool registry scales to 250 tools. Additionally, Nexus can splice compiled schema KV blocks into the live context, repairing the seam with a depth‑adaptive suffix redecode when rotary position embedding drift exceeds a threshold, ensuring output fidelity while achieving up to 1.7× TTFT speedup at moderate depth.
arXiv AI
Jul 14
Agentic Routing: The Harness-Native Data Flywheel
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.
arXiv AI
Aug 25
AgentWeave: Routing Before Reasoning for Efficient Function Calling in Tool-Rich Language Models
arXiv:2608.23078v1 Announce Type: new Abstract: Large language models increasingly operate over large collections of tools, functions, APIs, and specialized agents. As the candidate action space grow...