DecoR optimizes LLM routing via query decomposition and historical matching, achieving higher accuracy and reduced inference costs.

Bo Lv, Jingbo Sun

BrickAnything uses geometry-conditioned autoregressive modeling with structure-aware tokenization to generate stable, geometrically faithful brick structures, reducing rollback by 70%.

Zhengyang Ni, Feng Yan, Yu Guo et al.

Meta-Agent synthesizes and verifies task-specific multi-agent systems, reaching 82.7 average across six benchmarks.

Andy Xu, Yu-Wing Tai

Boosting inference with guided stochastic exploration: accuracy on Sudoku-Extreme improved from 85.9% to 98.0%.

Andrew Corbett, Archit Sood, Anna Tzatzopoulou et al.

PANDO improves multimodal AI agent efficiency via online skill distillation, achieving 58.3% success rate.

Yubo Li, Yidi Miao, Yuntian Shen et al.

FinCAD reduces look-ahead bias in financial backtesting via context-aware decoding.

Weixian Waylon Li, Mengyu Wang, Tiejun Ma

SAM introduces an external, state-adaptive memory system that significantly improves long-horizon reasoning, outperforming baselines with 8-10% gains on benchmarks.

Yuyang Hu, Hongjin Qian, Shuting Wang et al.

MOSS enables source-level self-rewriting in autonomous agents, boosting OpenClaw’s four-task mean grader score from 0.25 to 0.61 in one cycle.

Qianshu Cai, Yonggang Zhang, Xianzhang Jia et al.

LCGuard uses adversarially learned transformations on Transformer KV caches to reduce sensitive information reconstruction in multi-agent systems while preserving task performance.

Sadia Asif, Mohammad Mohammadi Amiri, Momin Abbas et al.

Directly evaluate harness optimizers via priority ranking; correlation ρ=0.602.

Kai Tzu-iunn Ong, Minseok Kang, Dongwook Choi et al.

Proposes three LLM-based planner generation methods—search code, PDDL models, and policies—focused on reliable, resource-efficient construction.

Michael Katz, Harsha Kokel, Kavitha Srinivas et al.

Insights Generator enhances LLM diagnostics with a multi-agent system, improving performance by 30.4pp.

Akshay Manglik, Apaar Shanker, Kaustubh Deshpande et al.

NeuroNL2LTL unifies neural translation with formal verification, achieving 28% semantic equivalence and 86% satisfiable formulas on 200,000+ requirements.

Paapa Kwesi Quansah, Ernest Bonnah

Proposes TaskGround framework for full-scene household reasoning, boosting success rates by over 20% and reducing input tokens by 18×.

ZhiYuan Feng, Yu Deng, Ruichuan An et al.

EXG uses experience graphs to enable self-evolving agents, achieving 150% improvement in task performance and 45.7% efficiency gains.

Yuxin Jin, Siyuan Zhang, Hanchen Wang et al.

A2RBench automates verifiable abstract reasoning benchmark generation, revealing LLMs' poor performance in abstract reasoning.

Qingchuan Ma, Yuexiao Ma, Yongkang Xie et al.

ECC algorithm calibrates semantic embeddings with model comparisons, improving LLM ranking by 17.64%.

Fangzhou Wu, Sandeep Silwal, Qiuyi Zhang

RAGA employs a read-search-verify-construct cycle with knowledge graph-vector synchronization, enabling autonomous KG lifecycle management with evidence provenance.

Chengrui Han, Zesheng Cheng

ShopGym combines ShopArena and ShopGuru to create realistic, scalable e-commerce environments for benchmarking AI agents, ensuring structural fidelity and reproducibility.

Chinmay Savadikar, Mingyu Zhao, Yuanzheng Zhu et al.

Flow-matching loss enables multi-strategy trajectory sampling, driving autonomous skill evolution.

Mingda Zhang, Tiesunlong Shen, Haoran Luo et al.