Tool-call judges evaluate argument values proposed by LLM agents. We find that they accept a correct value less often when their input holds no reference for it, that is, no text that says what the value should be. This happens when the value is a default value from the function schema that the user did not mention, when it has to be inferred, or when the text it comes from was cut from the judge input. We call this drop in acceptance the derivation gap. It appears across all seven judges we evaluate, including System One models CLM and Jev. The gap is not only a truncation artifact: correct default values have the largest gap on a benchmark with no truncation. A controlled source-relocation test shows that judges follow the reference in their input: they favor a visible incorrect value over a correct value whose source is hidden. We introduce DeRef (Derived Reference): a separate model reads the full history without seeing the candidate and writes a reference for the judge. Across three benchmarks, DeRef improves overall argument AUROC for all judges tested. On the controlled test, it raises AUROC from chance or below to between 98.40 and 99.59.
Translation pending · showing the source descriptionThe chart will appear after repeat observations. The current metric comes from the source.
0 source votesReal observations only. History before source connection is not reconstructed.
The study presents AgentSWE, a benchmark evaluating coding agents' ability to build agents aligned with user requirements. The research found that existing agents fail to accurately fulfill tasks, as there is a significant gap between demonstrated and actual performance.
5 days agoDaily PapersThe paper introduces S-Space, a linear subspace in multimodal language models where object-token representations encode continuous spatial coordinates. It demonstrates that S-Space serves as an internal workspace for spatial reasoning, enabling accurate spatial judgments through perception, internal reasoning, and selective verbal access, while highlighting limitations in spatial transformations across viewpoints.
5 days agoDaily PapersThe paper introduces TerminalHorizon, an automated data synthesis engine for long-horizon terminal agents. It constructs 1.5K task environments and fine-tunes Qwen3.5-27B to create TerminalHorizon-27B, achieving performance gains across multiple benchmarks. The model demonstrates improved ability to experiment, refine methods, and retain effective improvements in final results.
5 days agoDaily PapersUrbex is an agentic vision-language framework that reformulates grounding as active spatial search. It represents a city-scale 3D scene as an interactive multi-view environment, enabling a VLM agent to query landmarks, zoom into local regions, and commit grounded bounding boxes. Experiments show Urbex achieves the best Hit@1 and IoU on CityRefer.
yesterdayDaily PapersDetermining whether an image is AI-generated does not establish whether the situation it depicts is factually supported. We formulate Image Factuality Assessment: given an image and a generic verification instruction, a system returns a supported or refuted verdict with an evidence-grounded explanation. We introduce EviLens, an expert-reviewed benchmark of 10,174 supported and refuted images covering twelve factual error types.
4 days agoDaily PapersThe study explores Adversarial Heuristic Learning (AHL), where AI agents refine game strategies with fixed model weights. The AAArena benchmark includes 12 games and 1,920 archived programs, evaluated through protocols mimicking real competitions. Results show agents can improve strategies but face challenges in complex games.
6 days ago