Reading is not Reasoning: Bridging the Agentic Policy Gap in Vision-Text Compression

Multi-step language-model agents repeatedly process growing interaction histories, leading to substantial context costs. Vision--text compression reduces these costs by rendering history as images, but the resulting modality shift creates a marked capability gap. Through controlled evaluations of history recovery, matched-state decisions, and complete trajectories, we show that this gap cannot be explained by OCR quality alone. Visual-history agents exhibit systematic drift in action selection, query formulation, stopping, and evidence use, revealing an agentic policy gap. We introduce \textbf{CAPS}, a two-stage \textbf{C}ross-modal \textbf{A}gentic \textbf{P}olicy \textbf{S}elf-distillation framework that uses the same model's stronger text-history policy to supervise its visual-history counterpart. Offline trajectory self-distillation transfers successful text-policy behavior to visual-history inputs, while online policy self-distillation provides dense supervision on states visited by the visual-history policy during reinforcement learning. On SearchQA, CAPS improves over AgentOCR by 5.0\% and 3.4\% with 3B and 7B backbones, respectively. On full-history ALFWorld, the corresponding gains are 15.6\% and 14.5\%. Across settings, CAPS reduces average memory-context cost by up to 63.3\% and peak cost by up to 83.4\% relative to matched text-history policies. These results show that explicit cross-modal policy self-distillation can preserve agent capability under vision--text compression. Our code will be made publicly available in a future release.

LLM-as-a-Judge for Reliable and Explainable Offline Evaluation in Top-K Recommendation

Recommendation evaluation plays a crucial role in guiding the refinement and deployment of recommender systems. Most existing trials rely on offline evaluation using Top-K metrics computed over holdout user behaviors. However, we identify two fundamental limitations that undermine their ability to deliver reliable and explainable evaluations. Regarding reliability, offline evaluation treats observed user feedback as a proxy of true preferences and enforces rigid ID matching between the proxy and recommendation. In practice, feedback collections are inherently shaped by incomplete and biased item exposure, leading to distorted and unreliable assessments. Regarding explainability, Top-K metrics only establish numerical scores without offering meaningful insights to support them, thereby reinforcing the black-box nature of offline evaluation. In this paper, we propose a reliable and explainable LLM-as-a-Judge framework for offline recommendation evaluation. To enhance reliability, we introduce a semantic proxy from user textual behaviors to represent their true preferences. This proxy allows for more flexible matching between preferences and recommendations in the semantic space, rather than depending on the holdout feedback. To ensure explainability, the LLM Judge adopts a reasoning-then-scoring process to generate relevance judgments along with explicit rationale. Finally, we aggregate the individual scores into global Top-K metrics to quantify overall recommendation quality, and provide justification for each preference hit or miss. Extensive experiments demonstrate that the LLM Judge achieves solid reliability, explainability, and robustness in evaluation.

Measuring language complexity from hierarchical reuse of recurring patterns

We introduce the ladderpath index as a measure of language complexity grounded in algorithmic information theory. It counts the minimum steps needed to reconstruct a sequence through hierarchical reuse of repeated substructures, capturing an exactly computable but constrained form of algorithmic compressibility related to, but distinct from, Kolmogorov complexity. We apply the ladderpath approach to 21 parallel corpora from the Parallel Universal Dependencies dataset. The ladderpath index is approximately invariant across the languages, and varies much less than the corpus length. This is more pronounced when all corpora are mapped to a unified binary representation, providing evidence for the equi-complexity hypothesis from a representation-independent perspective. We also observe trade-offs between character inventory size and corpus length, and between vocabulary-level and corpus-level reconstruction complexity, supporting the trade-off hypothesis that total complexity is conserved and redistributed across linguistic levels. The reusable substructures identified by the ladderpath approach, without any linguistic input, overlap with words and morphological components attested in the natural vocabulary. The hierarchical reuse captured by the ladderpath approach parallels the chunking mechanisms proposed in cognitive science, where the human cognitive system compresses linguistic input into nested, reusable units under shared memory and processing constraints. This connection between cognitive chunking and the ladderpath approach provides a new interpretation for the equi-complexity and trade-off hypotheses, grounding both in the shared cognitive architecture that underlies language processing across human languages.

RubricBench: Aligning Model-Generated Rubrics with Human Standards

As Large Language Model (LLM) alignment evolves from simple completions to complex, highly sophisticated generation, Reward Models are increasingly shifting toward rubric-guided evaluation to mitigate surface-level biases. However, the community lacks a unified benchmark to assess this evaluation paradigm, as existing benchmarks lack both the discriminative complexity and the ground-truth rubric annotations required for rigorous analysis. To bridge this gap, we introduce RubricBench, a curated benchmark with 1,147 pairwise comparisons specifically designed to assess the reliability of rubric-based evaluation. Our construction employs a multi-dimensional filtration pipeline to target hard samples featuring nuanced input complexity and misleading surface bias, augmenting each with expert-annotated, atomic rubrics derived strictly from instructions. Comprehensive experiments reveal a substantial capability gap between human-annotated and model-generated rubrics, indicating that even state-of-the-art models struggle to autonomously specify valid evaluation criteria, lagging considerably behind human-guided performance.