arXiv:2512.18034v3 Announce Type: replace Abstract: Discrete facility layout design involves placing physical entities to minimize handling costs while adhering to strict safety and spatial constraints. This combinatorial problem is typically addressed using Mixed Integer Linear Programming (MILP) or Constraint Programming (CP), though these methods often face scalability challenges as constraint density increases. This study systematically […]
Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning
arXiv:2602.07830v2 Announce Type: replace Abstract: Time series is a pervasive data type across various application domains, rendering the reasonable solving of diverse time series tasks a long-standing goal. Recent advances in large language models (LLMs), especially their reasoning abilities unlocked through reinforcement learning (RL), have opened new opportunities for tackling tasks with long Chain-of-Thought (CoT) […]
PrefixGuard: From LLM-Agent Traces to Online Failure-Warning Monitors
arXiv:2605.06455v1 Announce Type: new Abstract: Large language model (LLM) agents now execute long, tool-using tasks where final outcome checks can arrive too late for intervention. Online warning requires lightweight prefix monitors over heterogeneous traces, but hand-authored event schemas are brittle and deployment-time LLM judging is costly. We introduce PrefixGuard, a trace-to-monitor framework with an offline […]
Prediction-Based Markov Violation Scores for Detecting Non-Markovian Observations in Reinforcement Learning
arXiv:2603.27389v2 Announce Type: replace-cross Abstract: Reinforcement learning algorithms assume that observations satisfy the Markov property, yet real-world sensors frequently violate this assumption through correlated noise, latency, or partial observability. Standard performance metrics conflate Markov breakdowns with other sources of suboptimality, leaving practitioners without tools to detect such violations. This paper introduces a prediction-based Markov Violation […]
Beyond Task Success: Measuring Workflow Fidelity in LLM-Based Agentic Payment Systems
arXiv:2605.06457v1 Announce Type: new Abstract: LLM-based multi-agent systems are increasingly deployed for payment workflows, yet prevailing metrics, Task Success Rate (TSR) and Agent Handoff F1-Score (HF1), capture only final outcomes or unordered routing decisions. We introduce the Agentic Success Rate (ASR), a trajectory-fidelity metric that compares observed and expected agent execution sequences at the transition […]
Measuring Black-Box Confidence via Reasoning Trajectories: Geometry, Coverage, and Verbalization
arXiv:2605.06308v1 Announce Type: new Abstract: Reliable confidence estimation enables safe deployment of chain-of-thought (CoT) reasoning through text-only APIs. Yet the dominant black-box baseline, self-consistency over K samples, is linearly expensive and ignores the geometry of the trace. We propose a black-box trajectory-confidence score: we embed a CoT as a sliding-window trajectory and measure its convergence […]
Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning
arXiv:2605.06116v1 Announce Type: new Abstract: Inference-time computation has greatly enhanced the performance of large language models (LLMs) on challenging reasoning tasks, but this strategy can incur high inference costs. One solution is to route intermediate chain-of-thought (CoT) states to language models of different sizes; however, existing approaches rely on handcrafted routing strategies that limit performance, […]
Rethinking Adapter Placement: A Dominant Adaptation Module Perspective
arXiv:2605.06183v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) is a widely used parameter-efficient fine-tuning method that places trainable low-rank adapters into frozen pre-trained models. Recent studies show that using fewer LoRA adapters may still maintain or even improve performance, but existing methods still distribute adapters broadly, leaving where to place a limited number of adapters […]
Temporal Smoothness Doubly Robust Learning for Debiased Knowledge Tracing
arXiv:2605.05958v1 Announce Type: new Abstract: Knowledge Tracing (KT) is fundamental to intelligent education systems, yet relies on educational logs that are selectively observed. The non-random nature of exercise recommendations and student choices inevitably induces severe selection bias. Most existing KT methods neglect this issue, training on observed logs using standard empirical risk, which yields biased […]
Pathways to AGI
arXiv:2605.06029v1 Announce Type: new Abstract: Our focus are five related questions that stem from a critical software studies perspective. Underpinning this view is the acknowledged need to avoid assumptions regarding the inevitability of the current situation relating to AI. What we need to see is the closeness of the linkage between current commercial AI development […]
PREFER: Personalized Review Summarization with Online Preference Learning
arXiv:2605.05911v1 Announce Type: new Abstract: Product reviews significantly influence purchasing decisions on e-commerce platforms. However, the sheer volume of reviews can overwhelm users, obscuring the information most relevant to their specific needs. Current e-commerce summarization systems typically produce generic, static summaries that fail to account for the fact that (i) different users care about different […]
XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction
arXiv:2605.05866v1 Announce Type: new Abstract: Multiphase powder X-ray diffraction (PXRD) analysis remains a fundamental bottleneck in structure identification, as real-world synthesis often produces complex mixtures whose constituent phases (components) cannot be reliably disentangled. While recent advances in representation-based crystal retrieval and generation suggest the possibility of inferring structures directly from PXRD, existing approaches largely assume […]