The paper presents an end-to-end system that translates high-level operator intents into low-level, safe routing constraints for LEO mega-constellations, achieving high accuracy and safety guarantees.

MViewRouter proposes a multi-view framework that internalizes geometric equivariance using a Multi-view Alternating Attention mechanism to improve generalization and stabilize training for combinatori…

The paper introduces R$^2$A, an adversarial attack that uses suffix optimization to mislead black-box LLM routers into consistently selecting expensive, high-capability models.

This paper presents CoEvoP&R, a framework that uses a large language model to automatically evolve analytical placement objectives, reducing post-route routed wirelength, congestion, and improving tim…

The paper introduces TRACE-Router, a task-level routing framework for large language models that aligns routing with the unit of supervision using delayed task feedback.

The paper proposes Predictive Routing Replay (PR2) to stabilize reinforcement learning on Mixture of Experts (MoE) LLMs by predicting and incorporating short-horizon router evolution during training a…

AlphaTransit introduces a novel search-based planning framework that combines Monte Carlo Tree Search (MCTS) with a neural policy-value network to efficiently design high-quality, city-scale bus trans…

The paper proposes RoRo, a rubric-guided process reward framework that improves stepwise model routing by evaluating the quality of intermediate reasoning steps, leading to better performance and cost…

This paper introduces the $k$-Step-Central Shortest Path problem to maximize reachability in transportation networks and provides a polynomial-time algorithm for unweighted graphs.

This paper proposes a budget-adaptive routing method for edge-cloud inference collaborations, which selects between weak-skipping and weak-conditioned placement based on offload budget.

The paper introduces GONDOR, a memory-efficient extension of Greedy Best-First Search (GBFS) that enables search continuation under strict memory constraints by periodically compressing the search tre…

The paper introduces RA-MoE, a novel fine-tuning framework that leverages the internal routing structure of Mixture-of-Experts (MoE) models to improve performance on multilingual downstream tasks by a…

This paper introduces the first LLM-generated, domain-independent heuristics for symbolic AI planning, using evolutionary search to surpass the performance of hand-engineered state-of-the-art methods.

This paper presents an optimized algorithm for computing cut sets of a path set in graph theory and introduces a vectorized computational framework for property calculations.

UniScale proposes a unified framework that jointly optimizes model routing and test-time scaling to achieve a superior, fine-grained quality-cost trade-off for large language model inference.

The ZCube topology, which eliminates path multiplicity and reduces switching hardware, delivers better performance for large model training and inference than traditional multipath datacenter networks…

The paper proposes BaSE, a multi-armed bandit approach, to optimally allocate a fixed budget of LLM calls across parallel evolutionary search trajectories, significantly improving mean fitness and rel…

This paper introduces Stigmergic Graph Memory (SGM), a method to improve warehouse throughput in many-to-many Multi-Agent Pickup and Delivery (MAPD) by using a bounded, decaying memory layer to record…