The article addresses the question of whether decision models like Jev can plan ahead. The author presents a methodology for evaluating planning ability using the Beeline metric, which measures the efficiency of solution search in various tasks.
The chart will appear after repeat observations. The current metric comes from the source.
17 source pointsReal observations only. History before source connection is not reconstructed.
CheckerBench is a benchmark for evaluating coding agents' ability to synthesize static-analysis checkers from defect specifications, including tasks derived from 300 CVEs across multiple repositories and language ecosystems. CheckerLab, an evaluation framework, measures diagnostic contrast, patch localization, and tool use, with results showing that current agents struggle to develop reliable checkers, achieving a maximum Pass@1 of 45.33%.
6 days agoDaily PapersTetris3D is a generative framework for 3D scene reconstruction from a single image, ensuring objects are geometrically and physically coherent. It uses explicit conditioning on surrounding objects' geometry and physical relationships, along with a physics-based dataset called ComOb for training and evaluation.
5 days agoDaily PapersThe paper investigates on-policy distillation (OPD) in cross-tokenizer settings, focusing on alignment coverage and supervision reliability. It finds that strict 1:1 token alignment covers most student-generated tokens despite vocabulary mismatches, and that restricting reverse KL to a top-16 subset of shared vocabulary achieves comparable accuracy to full shared-vocabulary OPD, while adding span supervision reduces accuracy.
6 days agoDaily PapersThe paper introduces Memento 3, a system enabling frozen LLM agents to continuously learn explicit world models through external memory. The agent maintains a natural-language rulebook as persistent semantic memory, which is compiled into executable code for prediction and planning. Through a loop of observation, reflection, and verification, the agent refines its model and uses verified updates to guide interaction. On ARC-AGI-3, the single-model agent achieves 100.0 mean Relative Human Action Efficiency and uses 44% of the human action count. In an Atari Pong case study, a learned feedback controller wins 21:0 in each of three evaluated episodes.
4 days agoDaily PapersThe paper introduces SGF+, a method for autoregressive video generation that decouples the roles of denoising and context writing by assigning separate parameters to each, improving visual quality and temporal consistency without additional training data or longer training periods.
5 days agoDaily PapersOpera is a verbal critic framework that treats each correction as a persistent note, followed until the diagnosed problem is resolved. It uses periodic and event-driven triggers to decide when to review, diagnoses issues with typed operators, and audits feedback before delivery.
4 days ago