arXiv:2605.22850v1 Announce Type: cross Abstract: Prefix KV caching has become a key mechanism in LLM serving: it reduces time to first token (TTFT) by avoiding redundant computation across requests that share a prefix (i.e., the system prompt). However, the accumulated KV cache is often larger than what GPU memory and local DRAM can hold. To […]
ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization
arXiv:2605.22885v1 Announce Type: new Abstract: Formal mathematics libraries are rapidly expanding, creating a growing need to refactor verified proofs for maintainability and to improve training data quality for neural provers. However, scalable proof optimization is hindered by heterogeneous and heuristically specified objectives, scarce data, and high training and inference costs. To overcome these challenges, we […]
BOHM: Zero-Cost Hierarchical Attribution for Compound AI Systems
arXiv:2605.22866v1 Announce Type: new Abstract: Compound AI systems route tasks through hierarchies of specialised components. Attribution is dominated by Shapley-based methods (SHAP), which decompose a coalition value function into per-component marginal contributions and require evaluation of the system on arbitrary component subsets. That requirement fails for third-party APIs, opaque endpoints, and agentic orchestrators that concentrate […]
Codec-Robust Attacks on Audio LLMs
arXiv:2605.20519v2 Announce Type: replace-cross Abstract: Prior attacks on Audio Large Language Models (Audio LLMs) demonstrated that carefully crafted waveform-domain perturbations can force targeted adversarial outputs. As a defense mechanism against these attacks, real-world codec compression preprocessing has been studied to both detect and remove the perturbations. Yet no existing attack has demonstrated robustness against these […]
Memorization Dynamics of Fill-in-the-Middle Pretraining
arXiv:2605.22981v1 Announce Type: cross Abstract: Fill-in-the-middle (FIM) is a pretraining objective widely used to equip causal language models with infilling ability, yet its effect on verbatim memorization remains underexplored. We study the memorization dynamics of FIM in a controlled setting by pretraining matched Llama 3.2 models with FIM and standard left-to-right (LTR) objectives on a […]
Worse than Random: The Importance of a Baseline for Unsupervised Feature Selection
arXiv:2605.22973v1 Announce Type: cross Abstract: Many novel unsupervised feature selection methods are proposed each year, yet their empirical evaluation is limited to supervised and unsupervised evaluation metrics computed on selected datasets, along with comparisons to existing methods. However, in the absence of an established evaluation baseline, it is difficult to determine the value added to […]
How Far Will They Go? Red-Teaming Online Influence with Large Language Models
arXiv:2605.22880v1 Announce Type: cross Abstract: As large language model (LLM)-based agents increasingly participate in online discourse, red-teaming their capacity to support political influence campaigns is critical for information integrity. In pursuit of this goal, we focus on locally deployed open-source LLMs, as opposed to frontier API-only models, given their superior alignment with the operational constraints […]
When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions
arXiv:2605.22873v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning has become the default strategy for enhancing LLM capabilities, yet its application raises a fundamental question: when is explicit reasoning actually beneficial? Empirical evidence reveals a striking paradox: CoT often provides marginal or even negative gains on factual and open-ended tasks while multiplying token consumption. In this […]
SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research
arXiv:2605.22878v1 Announce Type: new Abstract: The exponential growth of global academic output has confronted researchers and AI agents with an unprecedented “information explosion,” where fragmented and unstructured knowledge organization impedes deep interdisciplinary integration. Current academic retrieval tools predominantly rely on superficial keyword matching or vector-space semantic retrieval, which lack the topological reasoning capabilities required to […]
RMA: an Agentic System for Research-Level Mathematical Problems
arXiv:2605.22875v1 Announce Type: new Abstract: We present $textbfResearch Math Agents (RMA)$, an agentic framework for automated reasoning on research-level mathematical problems. Unlike prior studies centered on competition mathematics or formal theorem proving, RMA targets research-level mathematical problems that require long-horizon reasoning, literature grounding, and iterative proof refinement. RMA decomposes research-level proof solving into specialized modules […]
Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs
arXiv:2605.23039v1 Announce Type: cross Abstract: How do learners acquire knowledge of what is unacceptable without negative evidence? Construction Grammar proposes statistical preemption: exposure to a conventional form (e.g., “donated the books to the library”) preempts structurally possible but unattested alternatives (“*donated the library the books”). We present a computational study that, for the first time, […]
An Interpretable Closed-Loop Intelligent Tutoring System for Multimodal Affective Feedback in Asynchronous Presentation Training
arXiv:2605.17468v2 Announce Type: replace-cross Abstract: This paper presents an interpretable closed-loop Intelligent Tutoring System (ITS) that supports feedback-guided practice for developing on-camera oral presentation skills at scale. The system operationalizes a seven-dimensional Behaviorally Anchored Rating Scale (BARS) and implements a three-layer interpretable feedback architecture that connects rubric-aligned multimodal scoring, audience-perceived expressive diagnostics, and retrieval-augmented conversational […]