SkillGym is an automatic pipeline that generates verifiable environments for training skill-use agents. It crawls internet skills, filters for reproducible workflows, and uses a builder‑reviewer process to create difficulty‑controlled tasks with reference solutions and verifiers. The system builds 6.8k environments, collects 19k successful trajectories, and fine‑tunes LLMs from 2B to 122B parameters, improving performance and skill invocation rates.
By Renxi Wang, Mingshan Hee, Fajri Koto, Timothy Baldwin, Haonan Li
The paper introduces a method for co-evolving inspectable verifiers alongside self-improving agents. By synthesizing verifiers from clustered failures and selecting them based on agreement with a reference set, the authors demonstrate improved held‑out agreement on MBPP+ and outperform a bare LLM judge. They also show that removing anchor guards collapses the verifier into a vacuous grader, yet the collapsed verifier still trains skills effectively, indicating that downstream task scores cannot certify a self‑evolved verifier.
By Xing Zhang, Guanghui Wang, Yanwei Cui, Ziyuan Li, Wei Qiu, Bing Zhu, Peiyang He
arXiv:2606.28876v4 Announce Type: replace-cross
Abstract: Memory-Mediated Learning Architecture (MMLA) separates slow base parameters theta, a bounded numerical policy carrier Phi, and a bounded auth...
By Junyi Zou, Avrova Donz
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 SMITH, a reinforcement learning framework that jointly trains large language models to create and use tools within a single policy. By alternating between build and use tasks and employing separate reward signals for schema, code, and outcome failures, SMITH enables a 4B Qwen3 model to achieve state‑of‑the‑art accuracy on procedural reasoning benchmarks, outperforming larger untrained models and improving performance on downstream tasks when its tools are applied.
By Zhi Rui Tam, Chieh-Yen Lin, Yun-Nung Chen, Shao-Hua Sun, Hung-yi Lee
arXiv:2608.22533v1 Announce Type: new
Abstract: Autonomous computer-use agents are increasingly applied to long-horizon tasks requiring coordinated application calls, persistent state tracking, and v...
By Zheyuan Deng, Binghang Lu, Hanqi Feng, Shirley Huang, Dianzhuo Wang, Yuanda Xu, Zhiwei Zhang, Yige Sun, Changhong Mou, Runyu Zhang, Yuexing Hao, Barnabas Poczos, Xiaomin Li
arXiv:2609.38142v1 Announce Type: new
Abstract: A small trainable advisor can steer a frozen language-model executor using natural-language advice. In addition to learning from task rewards, the advi...
By Rishabh Agrawal, Hejie Cui, Shasha Li, Shanchan Wu, Sercan \"{O}. Ar{\i}k
arXiv:2607. 23386v1 Announce Type: new Abstract: We document a failure class in frontier large language models -- exception chain collapse -- observed in eligibility evaluation under nested conditional rules of the form "A is required UNLESS B applies, UNLESS C overrides B".
By Paul Simpson, John Kozak, Lisa Doake
arXiv:2605. 14084v2 Announce Type: replace-cross Abstract: Code agents must both reason over long-horizon repository state and obey strict tool-use protocols.
By Mingzhi Zhu, Michele Merler, Raju Pavuluri, Stacy Patterson
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
arXiv:2605. 17554v2 Announce Type: replace Abstract: Frontier deep research agents (DRAs) plan a research task, synthesize across documents, and return a structured deliverable on demand.
By Tanmay Asthana, Aman Saksena, Divyansh Sahu
arXiv:2605. 29668v2 Announce Type: replace Abstract: LLM agents acting in structured environments fail in operational rather than conversational ways, and reliability depends on procedural knowledge of the environment.
By Johannes Moll, Jean-Philippe Corbeil, Jiazhen Pan, Martin Hadamitzky, Daniel Rueckert, Lisa Adams, Keno Bressem