The paper reports on training and calibration experiments for three open models on the ARC‑AGI‑2 benchmark, using offline runs on four L4 GPUs for up to 12 hours. For the NVARC Qwen3‑4B grid model, a curated corpus of 12,000 executable rules and 95,993 tasks was built, and fine‑tuning on 1,920 real task records raised the semi‑private score from 28.96 to 33.06, with no synthetic‑task checkpoint outperforming the real‑task model. For the Qwen3.8‑27B reasoning model, fine‑tuning on 1,036 of its own reasoning traces and a specialized inference procedure increased the score from 26.81 to 44.03, while the Qwen3.8‑Flash‑Next mixture‑of‑experts model achieved a best score of 56.67 after expert pruning, routing statistics adaptation, and an FP8 indexer cache.
By Nguyen Minh Thang, Trinh Thi Phuong
The paper introduces Zep Agent Skills, a production service that autonomously compiles and curates procedural memory for large language model agents by converting verified execution traces into versioned skills. It records each task attempt as a trace, uses a compiler with Reflector and Curator roles to transform verified traces into skills, and applies admission gates and search ranking based on verified outcomes. The open Agent Skills format, originally from Anthropic, allows any host to load compiled skills, and evaluation on several benchmarks shows significant performance gains for weaker executor models without additional training.
By Daniel Chalef, Peter Evans, Pavlo Paliychuk, Mehul Patel, Preston Rasmussen, Jack Ryan
arXiv:2601. 22758v2 Announce Type: replace Abstract: Large language model agents repeatedly encounter related tasks, yet systems that learn from trajectories commit every lesson to one predefined artifact form.
By Libin Qiu, Zhirong Gao, Junfu Chen, Yuhang Ye, Liangyu Li, Weizhi Huang, Xiaobo Xue, Wenkai Qiu, Shuo Tang
arXiv:2606. 31630v1 Announce Type: new Abstract: Language models increasingly write probabilistic programs (in NumPyro, Stan, or Pyro), but a program that compiles, runs, and passes every unit test can still be \emph{statistically} wrong -- a Gaussian likelihood for heavy-tailed data, a Poisson for over-dispersed counts, an invalid prior support, or a pathological parameterization.
By Jian Xu, Delu Zeng, John Paisley, Qibin Zhao
arXiv:2608. 10333v1 Announce Type: new Abstract: LLM agents execute heterogeneous sequences of model calls within a single task: some invocations require careful reasoning, while others are structured steps such as formatting or tool-argument construction.
By Yuhang Yao, Zeyu Wang, Wanyi Chen, Tongyun Yang, Yuhang Han, Jie Xiao, Chengke Bao, Tianyi Zhao, Lynn Ai, Eric Yang, Tianyu Shi
arXiv:2606. 00671v3 Announce Type: replace Abstract: We present Moxia (formerly AXIOM), a trust-first neuro-symbolic architecture for self-explaining mathematical reasoning over natural-language input.
By Alessio Bruno
arXiv:2606. 10457v1 Announce Type: new Abstract: Decision rules that enterprise experts apply tacitly -- in auditing, compliance, and contract review -- can be systematically recovered and improved through iterative error analysis.
By Junli Zha, Jinbo Wang, Chao Zhou, Xiang Song
PROOF-Gen is a method that improves distillation of tool‑calling models by recovering successful trajectories from teacher failures. It uses per‑scenario prompt optimization to generate corrective guidance that steers the teacher to a passing trajectory, then removes this guidance before training so the student learns from clean demonstrations. On τ2‑bench, PROOF-Gen recovers 93% of failed scenarios, boosting Qwen3‑4B‑Instruct‑2507’s Pass^1 from 0.132 to 0.529 and improving Gemma 4 E4B‑it by 7.2pp on BFCL v4 multi‑turn, while also raising deployed on‑device model performance by up to 5.0pp across response‑quality metrics.
By Anh Ta, Junjie Zhu, Shahin Shayandeh
arXiv:2608. 15089v1 Announce Type: new Abstract: Long-horizon agents can fail even when their underlying models can solve the constituent steps.
By Ziheng Qin, Yaxin Lu, Zhangyang Atlas Wang, Kai Wang
arXiv:2605. 22148v3 Announce Type: replace Abstract: A large language model (LLM) agent that writes and edits its own skill library must also decide which skills to keep, from one noisy scalar per skill.
By Xing Zhang, Yanwei Cui, Guanghui Wang, Ziyuan Li, Wei Qiu, Bing Zhu, Peiyang He
The paper introduces RefineCut, an open‑weight planner that edits a typed video timeline by applying structured patches for clip selection, trimming, ordering, transitions, music alignment, and duration. A deterministic verifier checks each patch against an explicit constraint ledger, and the planner is trained via verifier‑replayed distillation and a second evolutionary stage (RefineCut‑Evo) that uses the verifier and a task rubric to generate high‑margin preference pairs. On the RefineCut‑Bench dataset, the 8‑billion‑parameter planner improves from a Video‑Editing Score of 0.620 to 0.924, matching or exceeding its frontier teachers in a closed verifier loop, and the gains transfer to other large models such as Llama‑3.1‑8B and GLM‑4‑9B.
By Haoyu Wang, Cheng Feng, Liuyang Bian, Ruiyang Huang, Lei Wei, Yafei Wen, Xiaoxin Chen, Xiaoying Tang
EKLAV is a method that uses a teacher’s chain‑of‑thought (CoT) reasoning as privileged input while supervising only the final answer. By strategically placing parts of the trace in the prompt, EKLAV improves ranking performance on BRIGHT passage reranking and table‑reranking benchmarks, outperforming full‑trace distillation and answer‑only training. The approach reduces training compute and inference time, and the generated traces show more efficient reasoning patterns.
By Adarsh Singh, Aman Singh, Kushal Raj Bhandari, Soham Dan, Anoop Kumar, Vivek Gupta