arXiv:2610.35077v1 Announce Type: cross Abstract: Understanding and operating with scientific charts is a standard approach in data analysis, and while humans are good at interpreting such charts, op...
arXiv:2608. 06933v1 Announce Type: cross Abstract: Today, we improve models by training and evaluating them on problems at the frontier of their abilities.
ExpEvolve introduces idea-level extraction and control into evolutionary coding agents, enabling the discovery of high-level factors that explain differences in program performance. By leveraging these factors, the framework guides both exploitation of existing experience and exploration when progress stalls, leading to significant gains in sample efficiency and final performance. Across 11 open-ended mathematical tasks and additional benchmarks, ExpEvolve improves results by up to 5.0× and transfers benefits to other large language models and machine learning tasks.
The paper introduces EviSpec, a training‑free compiler that generates complementary evidence specifications to improve high‑resolution multimodal large language models (MLLMs). By explicitly guiding visual search with structured evidence specifications, EviSpec achieves significant relative gains—up to 14.8% over random evidence—across five MLLMs and three benchmarks, and also sets new state‑of‑the‑art results on VQA and hallucination‑focused tasks.
The paper reports on a verifiable‑reward tuning approach applied to an Ornith‑style vision‑language model for multi‑view driving question answering. Using a 256‑token limit, the GRPO method raises answer extraction from 78.25 % to 90.25 % and accuracy from 55.50 % to 63.75 %. On a larger 2,511‑question set, the tuned pipeline cuts average token usage from 108.6 to 47.1, though the accuracy improvement is not statistically significant.
arXiv:2606. 01286v1 Announce Type: cross Abstract: The rapid progress of frontier large language models has led to widespread benchmark saturation, limiting the ability of existing datasets to differentiate model capabilities or provide useful training signal.
VICO proposes a co‑evolutionary framework where a vision‑language model (actor) and an Environment‑as‑Rewriter (EnvRewriter) are trained together. The EnvRewriter edits visual structures—such as scene graphs, chart tables, or protected region masks—to generate new training samples whose difficulty is calibrated to the actor’s current performance via a pass‑rate reward. Across nine multimodal benchmarks, VICO‑8B outperforms its base model by up to +5.0 % on out‑of‑domain tasks and surpasses other co‑evolution baselines while requiring far fewer labeled samples.
arXiv:2606. 11719v1 Announce Type: cross Abstract: Spatial reasoning remains a persistent challenge for multimodal large language models (MLLMs).
arXiv:2604. 08477v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has substantially improved reasoning in formal domains such as mathematics and code, but extending these gains beyond STEM remains challenging.
The paper introduces a self‑evolving harness framework where a frozen language‑model agent first solves tasks and then edits its own harness based on run records. Using a 49‑line seed harness, the evolved harness improves average scores on in‑distribution benchmarks by 4.48 points and on out‑of‑distribution benchmarks by 12.64 points, surpassing Codex on the former and matching it on the latter. Continued evolution on a specific out‑of‑distribution benchmark further raises performance, and the study analyzes emergent mechanisms such as output truncation and history compaction.
arXiv:2606. 26294v1 Announce Type: cross Abstract: Self-improving agents are state-of-the-art (SOTA) on agentic coding benchmarks and have recently been extended to general domains.
arXiv:2608. 15303v1 Announce Type: new Abstract: Test-time compute can substantially improve Large Language Model (LLM) reasoning performance, yet how and when additional compute helps remains poorly understood.