Search posts, papers, and topics
Reproduces Mold’s linker benchmarks on a 16‑core Ryzen, shows that configuration (filesystem, delete‑output, fork) explains most of the Wild vs Mold speed gap, and notes recent Mold releases and upcoming Wild tweaks that close the gap.
The paper presents RecreationWorld, a five‑platform framework that lets hybrid computer‑use agents learn by recreating the behavior of a running reference, and introduces RecreationBench, a 250‑task benchmark with programmatic and visual assertions. Experiments show GPT‑6 Astra reaches 58.1% overall but struggles with deeper programmatic tests, highlighting gaps in current agents.
ProgramDistill is a new benchmark that automatically extracts 1,975 replay‑verified feature behaviors from 26 real web apps, builds 4,063 coding‑agent tasks, and measures how well state‑of‑the‑art agents (e.g., GPT‑6 Astra, Claude Opus 5) can reconstruct full or partial applications, revealing steep drops in success as restoration depth grows.
The authors present VākQA, a 2,001‑question spoken factoid QA benchmark for Telugu with audio, transcriptions, and human‑verified answers, and they validate automatic evaluation methods against human ratings. Using this setup they show that translation loses cultural nuance, ASR errors alter meaning, and cascaded ASR‑MT errors degrade model performance.
OmniVChat defines native audio‑visual dialogue where a model consumes raw audio and video streams and replies in text. The authors build OmniVChat‑Studio, a multi‑agent simulator that generates single‑ and multi‑turn audio‑visual conversations, and use it to create OmniVChat‑Bench, a benchmark covering five dialogue abilities. They also propose OmniVChat‑RL, a reinforcement‑learning reward that b…
UFO introduces an Atomized Chain‑of‑Evaluation (AEU) framework that breaks omni‑condition alignment in multi‑modal image generation into a sequential set of fine‑grained checks, achieving a 15.25 % boost in correlation with human judgments. The authors also release UFO‑Bench, a benchmark for testing how well models satisfy combined textual and visual conditions.
VA‑Bench is a new benchmark that evaluates general‑purpose multimodal LLMs on the full observe‑reason‑act‑revise loop in embodied robotics, using RGB demonstrations, active camera control, and metric Cartesian commands. The best model reaches 53.9% average task success, showing active perception helps but long‑horizon tasks remain unsolved.
OmniVBench is a new benchmark and the Omni‑R2V Dataset, offering 7 task families, 18 fine‑grained reference‑to‑video generation tasks and a factor‑grounded evaluation checklist of over 12 k items. The dataset provides 340 k industrial‑grade video samples and pipelines for constructing reference‑target pairs, exposing large performance gaps in current R2V models.
PANORAMA introduces a VLM that grounds each phrase of a caption to pixel masks by selecting from a phrase‑conditioned pool of mask proposals, trained jointly with caption generation. It sets a new benchmark on the PanoCaps dataset and outperforms prior methods on several pixel‑level grounding tasks.
CADWorld is a new benchmark suite of 200 long‑horizon mechanical CAD tasks in FreeCAD, covering sketching, part modeling, assembly, CAM, FEM, and more. Agents interact via screenshots and GUI actions; success is checked by executable validation of the saved CAD artifacts. Seven existing agents achieve at most 17.5 % success versus an 87 % expert baseline, highlighting the gap between GUI competen…
The paper presents REVERSAL‑BENCH, a benchmark that varies environment reversibility with a parameter ρ and provides a ground‑truth reset oracle for eight manipulation tasks. Using it, the authors show that reset‑free RL agents hit a sharp reversibility cliff and become permanently trapped, while episodic agents remain robust.
E2A‑Bench is a 969‑query benchmark for financial chart reasoning that evaluates vision‑language models across a full evidence‑to‑action chain using four metrics (UCR, RCI, ECI, NDR). Experiments on 20 VLMs expose hidden failures: low‑UCR models have only 6.4 % directional coverage, oracle‑aided verification cuts unsupported claims but can kill coverage, and fine‑tuning inflates BUY:SELL ratios by…
APort Vault is a benchmark that replays 4,371 human‑written attacks against a live payment‑handling AI agent across 14 models and multiple policy configurations, generating 225,964 evaluations. Adding the Open Agent Passport pre‑action check eliminated all unauthorized transfers in the test, showing a per‑session breach upper bound of 0.38%.
