GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis

GraphForge synthesizes workspace tasks and verifiers over real file evidence graphs to train working agents, and fine-tuning Qwen3.6-27B improves GDPVal, Workspace-Bench-Lite, and SpreadsheetBench II results.

Qisheng Su, Hanchen Wang, 朱冠儒, Huicheng Jiang and 8 more

Published Sep 30, 2026 · 0 citations · ▲ 146 on Hugging Face

Does Learning Protein Folding Generalize to Broader Reasoning?

Post-training on protein-folding data via discrete answers and continuous geometry improves structure prediction and broad reasoning across ten benchmarks.

Yong Liu, Zhanpeng Shi, Yizhou Dang, Zhongyue Zhang and 3 more

Published Sep 30, 2026 · 0 citations · ▲ 120 on Hugging Face · Code ★ 28

WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents

WEFT evolves whole agentic interaction systems for tool-use post-training, outperforming environment-scaling baselines by up to 12.27 points across benchmarks.

Bo Mao, Hang He, Linting Wang, Lizhi Lin and 16 more

Published Sep 29, 2026 · 0 citations · ▲ 19 on Hugging Face

Multilinguality in Hybrid Attention LLMs

Hybrid attention LLMs develop cross-lingual alignment tied to recurrent and full-attention layer ordering, with a spike at the first full-attention layer; distillation shows starting with full attention learns up to 2.5× faster.

Lucas Bandarkar, Junlin Hu, Chenyuan Yang, Mohsen Fayyaz and 1 more

Published Sep 28, 2026 · 0 citations · ▲ 2 on Hugging Face

Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features

Existing token-reweighting methods cannot reverse harmful SFT features; SCALE uses frozen SFT deltas with entropy-guided gates to suppress, reverse, or extrapolate them, improving math and code results.

Cunchun Li, Haonan He, Yifan Gao, Minglei Li and 3 more

Published Sep 27, 2026 · 0 citations · ▲ 11 on Hugging Face

OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution

OpenART scales agent red teaming via open-ended environment evolution across 10,000 stateful scenarios, with EMHA achieving 85% attack success that grows with complexity.

Yunhao Chen, Xin Wang, Yixu Wang, Yi Liu and 5 more

Published Aug 1, 2026 · 0 citations · ▲ 266 on Hugging Face · Code ★ 231

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

SkillOpt treats agent skills as external state optimized via bounded text edits validated on held-out scores, improving accuracy up to 24.8 points with stable transfer.

Yifan Yang, Ziyang Gong, Weiquan Huang, Qihao Yang and 11 more

Published May 22, 2026 · 2 citations · ▲ 267 on Hugging Face · Code ★ 18,090

AI Can Learn Scientific Taste

RLCF trains AI to judge and propose high-impact research ideas via community feedback, showing learned scientific taste generalizes across fields and time.

Jingqi Tong, Mingzhe Li, Hangcheng Li, Yongzhuo Yang and 19 more

Published Mar 15, 2026 · 0 citations · ▲ 316 on Hugging Face · Code ★ 433

Benchmark^2: Systematic Evaluation of LLM Benchmarks

Benchmark² evaluates LLM benchmarks via ranking consistency, discriminability, and capability alignment deviation, revealing quality variations and enabling smaller effective test sets.

Qi Qian, Chengsong Huang, Jingwen Xu, Changze Lv and 12 more

Published Jan 7, 2026 · 0 citations · ▲ 34 on Hugging Face

MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues

MT-Video-Bench introduces a multi-turn dialogue benchmark that evaluates multimodal LLMs on holistic video understanding.

Yaning Pan, Qianqian Xie, Guohui Zhang, Zekun Moore Wang and 12 more

Published 2026 · 0 citations · Code ★ 21

Revisiting the Negative Data of Distantly Supervised Relation Extraction

Distantly supervised relation extraction treats unlabeled data as negative, but analysis reveals hidden positives and noisy labels cause false negatives. Cleaning negative data improves model training and extraction performance significantly.

Chenhao Xie, Jiaqing Liang, Jingping Liu, Chengsong Huang and 2 more

Published 2021 · 24 citations

Agents as Neuro-Symbolic Reasoners: Path Feasibility Reasoning for Precise Static Bug Detection

Xueying Du, Kai Yu, Chong Wang, Yi Zou and 4 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Causally Structured Differential Network Modeling for Single-Cell Perturbation Prediction

Jiayi Dong, Xinyue Gu, Fei Wang

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Self-Calibrated GUI Reward Model via Inverse Dynamic Modeling

Zeyi Sun, Shengyuan Ding, Xingpeng Xia, Jinsong Li and 3 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Large Discrete Policy: Advancing Explicit Behavior Modeling with Stochastic Iterative Scoring

Zhenxin Li, Nadine Chang, Xinglong Sun, Jingde Chen and 7 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

StableAvatar: Ultra-Long Audio-Driven Avatar Video Generation

Shuyuan Tu, Yueming Pan, Yinming Huang, Xintong Han and 5 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Advanced Routing as Regularization Allocation for Efficient Diffusion Transformer Training

Qin MA, XIAOQI SUN, bo li, Yuquan Zhou and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Fast Algorithms for the Label Propagation Operator on Signed Graphs

Yubo Sun, Zhongzhi Zhang

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Full-Atom Cyclic Peptide Design via Test-Time Scaled Autoregressive Flow Matching

Yunpeng Wang, Zhonghui Gu, Runze Ma, Jie Yang and 5 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

FogGS: Physics-Grounded 3D Foggy Effects

Jiaxin LI, Tailin Wu, Jiankang Deng, Li Zhang and 1 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026