ExplorationBench is a framework for evaluating AI systems' ability to explore and discover new knowledge in verifiable alien worlds, where hypotheses must be tested through experimentation rather than relying on pre-trained data. It includes two sandboxes, AlienCode and AlienLogic, with multiple tasks designed to challenge systems' exploration and problem-solving skills.
The chart will appear after repeat observations. The current metric comes from the source.
1 source votesReal observations only. History before source connection is not reconstructed.
This benchmark helps evaluate how well AI systems can explore and discover new knowledge in unfamiliar environments, which is crucial for advancing scientific discovery and autonomous learning.
The paper introduces Taste-Bench, a benchmark for evaluating an agent's 'taste' in making long-horizon decisions. It measures the ability to choose the better path in decision forks without knowing future outcomes, revealing that current models perform poorly and that taste can be improved through distillation.
3 days agoDaily PapersThe paper introduces Document Retrieval-Aware Chunking (D-RAC), a method for efficiently processing enterprise documents by normalizing them into PDF and converting them into retrieval-optimized Markdown using a multimodal LLM. This approach preserves document structure, reduces token costs, and improves chunking efficiency compared to traditional methods.
4 days agoDaily PapersHappyWorld-Bench is a comprehensive benchmark for evaluating the reliability of generated worlds under interaction, exploring their consistency and responsiveness. It includes three tracks—video, spatial, and embodied world models—with 1,138 video prompts, 300 spatial scenes, and 254 embodied test cases. The benchmark uses human A/B comparisons and automated metrics to assess behavioral correctness and model performance across 14 video, 9 spatial, and 8 embodied systems.
4 days agoDaily PapersThis paper introduces an all-in-one multilingual scene text recognition system that uses a script-aware Mixture-of-Experts (MoE) architecture. The system, called ScriptMoE, outperforms existing methods on multilingual text recognition tasks by leveraging a large synthetic dataset and a lightweight architecture that shares a visual encoder while using script-specific experts for decoding.
4 days agoDaily PapersOmniEdu is an open family of foundation models designed for K-12 education, focusing on problem solving, curriculum understanding, diagnostic reasoning, and instructional support. The models are trained on a diverse dataset of educational resources and evaluated on multiple benchmarks, showing strong performance in educational tasks.
6 days agoLessWrongThe post explores the author's confusion about how neural networks, particularly large language models (LLMs), perform and learn computations. It challenges the conventional 'mechinterp' (mechanistic interpretation) approach that relies on circuit-based explanations, arguing that 'circuits' and 'computation' may not be the most suitable framework for understanding LLMs. The essay discusses representational drift as a key obstacle to weight-based circuit analysis and suggests a 'co-selectionist' view of circuits as emergent units. The author also reflects on how the concept of 'universality' should influence explanations of LLM function.
3 days ago