Jinshan Gao, Zhuoran Jin, Tianyi Men, Kang Liu, Jun Zhao · Aug 31, 2026 · Citations: 0
Automatic MetricsGeneral
Large language model-based multi-agent systems are evolving from fixed interaction topologies toward dynamically orchestrated Agent Swarms.
We propose SwarmBench, a benchmark that evaluates model performance from multiple perspectives, including accuracy, efficiency, cost, and process quality.
To address this, we propose Posterior Label Correction DPO (PLC-DPO) to robustly optimize preferences by routing each pair's training signal as a clean, flip, or tie case.
Across 57 dataset-model-benchmark cells, PLC-DPO obtains the best mean win rate against DPO (60.5 vs.
Benchmark saturation and data contamination increasingly obscure genuine scientific reasoning in frontier LLMs.
We introduce ScienceArena, an olympiad-style benchmark from thirteen public science competitions in physics, chemistry, and biology, including IPhO and IChO 2025--2026, IBO 2023, USAPhO 2026, and USNCO 2025.
Cheng Gu, Qiusheng Zhao, Anbang Liu, Shaochong Lin, Max Z. J. Shen · Aug 31, 2026 · Citations: 0
Simulation EnvGeneral
Large-scale industrial robot fleets share constrained physical infrastructure, making vehicle travel times dependent on safety separation, intersection access, downstream blocking, and station contention.
Doyun Kim, Chanwoo Kim, Sugyeong Eo, Yeo-Chan Yoon, Chanjun Park · Aug 31, 2026 · Citations: 0
Red TeamGeneral
LLM-based agent systems increasingly adopt skill-based architectures to reduce repetitive reasoning costs and improve stable, efficient task execution.
Recent studies propose self-evolving agents that autonomously generate, refine, and reuse skills from past experiences to enable continuous capability evolution.
Jinyoung Kim, Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim, Moontae Lee, Honglak Lee · Aug 31, 2026 · Citations: 0
Pairwise PreferenceCritique EditGeneral
We use this reward to train an actor-tailored critic with GRPO, and use critique-guided refinements to construct DPO preference pairs for the actor, forming a co-evolving critic-actor loop where the critic adapts to the actor's changing…
Yanqi Yu, Pingwei Sun, Jianchao Tan, Tao Zhang, Yuchen Xie, Xunliang Cai · Aug 31, 2026 · Citations: 0
Automatic MetricsGeneral
Across retrieval and end-to-end reasoning benchmarks on Kimi-Linear, conservative DASC configurations remain close to full caching while compressing KDA recurrent state checkpoints by 2.63\times.
Hanlin Tian, Minhao Li, Yu Mi, Sihan Zhu, Zhao Yang, Yuxiang Wang · Aug 31, 2026 · Citations: 0
Rubric RatingGeneral
Professional agent tasks often depend on conventions that are absent from public corpora, yet benchmarks rarely control whether an agent has access to those conventions.
Across fifteen calibration tasks, one frontier agent configuration achieves a 68.0% pass rate with the artefact and 0% without it; on one task, a plausible but incorrect artefact also yields 0% across five trials.
Haoran Wang, Jing Yao, Xu Yang, Zeqing Wang, Yang Zhang, Pedram Ghamisi · Aug 31, 2026 · Citations: 0
Expert VerificationGeneral
The unprecedented surge in Earth observation data volume and diversity has exposed a critical bottleneck for traditional manual workflows, catalyzing the emergence of Remote Sensing (RS) Agents.
However, the practical deployment of these advanced agents is severely hindered by their heavy reliance on large-scale general-purpose LLMs, which lack deep domain expertise and impose prohibitive infrastructure demands.
Centering better resolves subset diversity but loses this useful token-wise preference, revealing that diversity and distinctiveness are entangled in the raw geometry.
Based on this analysis, we propose the Centered Geometry Pruner (Cen-Prune), which measures subset diversity using centered cosine similarity while retaining raw-space distinctiveness as a complementary token-wise preference.
To bridge this gap, we present MTPaperBananaBench, a benchmark for multi-turn diagram generation containing 292 images annotated with 3,518 user requirements.
To address these issues, we introduce PaperBanana-Interact, a multi-agent system that refines diagrams via an internal critique-and-refine loop.
