The paper introduces T1, a 122‑billion‑parameter Mixture‑of‑Experts model trained with reinforcement learning to perform long‑horizon terminal tasks such as coding and scientific discovery. T1 operates a real shell in a cloud sandbox, making over 300 tool‑call turns per task and receiving rewards from task‑specific verifiers. The authors detail a training recipe that includes aggressive warm‑starting, TITO construction with drift repair, and rollout‑routing replay, achieving significant performance gains on Terminal‑Bench 2.1 and surpassing GPT‑5.4 and GLM‑5.1 on the Long‑Horizon Terminal Bench.
By Junyao Yang, Yucheng Shi, Zhongzhi Li, Ruhan Wang, Zongxia Li, Haitao Mi, Leowei Liang
arXiv:2609.40063v1 Announce Type: cross
Abstract: Low-Rank Adaptive Residual Connections (LARC) give a frozen model a compact numerical state that can learn from feedback. The map $h+BAh$ adds a low-...
By Junyi Zou, Avrova Donz
arXiv:2608. 05475v1 Announce Type: new Abstract: Task knowledge is commonly stored either as text in the prompt or as an update to model weights.
By Zhaowei Han, Xiang Zhang, Bing Han, Kai Liu, Danqi Hu, Jie Liu
arXiv:2609.15982v1 Announce Type: cross
Abstract: Skills extend an LLM agent beyond its parametric knowledge, and the gain they promise rests on picking the right one. Deployed harnesses route by pre...
By Ruishuo Chen, Xun Wang, Yu Chen, Zhuoran Li, Longbo Huang
arXiv:2609.13058v1 Announce Type: new
Abstract: Reinforcement learning (RL) has become central to post-training of large language models. Recent advances in RL for Mixture-of-Experts (MoE) models hav...
By Hongyi He, Zhenghao Lin, Xiao Liu, Peng Cheng, Yan Lu, Yeyun Gong
arXiv:2607. 09375v1 Announce Type: new Abstract: We present Mach-Mind-4-Flash, a 35B-parameter Mixture-of-Experts (MoE) agentic model with 3B activated parameters.
By Foundation Model Team
arXiv:2608. 09168v1 Announce Type: new Abstract: Agent skills are increasingly used to equip large language model (LLM) agents with reusable procedural knowledge.
By Liang He, Jingbo Wen, Hongyu Gu, Hao Li, Haoyu Wang, Yixiong Chen, Kangning Cui, Xilu Wang
The paper introduces Reinforcement Learning with Decomposed Subtasks (RLDS), a method that splits trajectory rewards into per‑subtask shares before policy updates, replacing the scalar advantage used in Group Relative Policy Optimization (GRPO). RLDS employs Subtask‑Decomposed Advantage Estimation (SDAE) to compute group‑relative advantages and distribute credit to tokens based on subtask importance, focusing on steps where a reflection marks a subtask as consequential. Experiments on four benchmarks—FrozenLake, HotpotQA, ScienceWorld, and DeepResearch—show that RLDS improves performance on high‑heterogeneity tasks (ScienceWorld and FrozenLake) and is more compute‑efficient than scalar GRPO for long rollouts.
By Mattie Terzolo, Mikolaj Sacha, Ayan Sinha, Andrew Rabinovich
arXiv:2610.02359v1 Announce Type: cross
Abstract: Reinforcement learning from verifiable rewards (RLVR) usually optimizes answer correctness, yet useful language-model behavior also requires high-qua...
By Doseok Jang, Jon Ander Campos, Youran Qi
The paper introduces CoPE, a method that trains language agents by adding multi‑step action targets to the policy backbone. By supervising each action forecasted from preceding histories, CoPE enables acting and forecasting to co‑evolve without extra inference cost. Across five benchmarks, CoPE outperforms existing RL baselines, achieving up to twice the sample efficiency on ScienceWorld and improving overall performance on realistic applications.
By Haofei Yu, Yixing Chen, Yining Zhao, Xuyan Ye, Yuxiang Liu, Zhigang Hua, Yan Xie, Shuang Yang, Jiaxuan You
The paper introduces READ, a method for composing low‑rank adapters (LoRA) in large language models. By rewriting each adapter into a balanced canonical form and enforcing a one‑directional coupling, READ allows new skills to read but never write into the output subspaces of existing skills, eliminating interference. Experiments on four benchmark suites and two model families show that READ consistently outperforms existing baselines, improving SuperGLUE scores by over twenty points and domain suite scores by more than seven points.
By Zeyan Li, Panqi Yang, Qirong Guo, Shengda Zhuo, SIyuan Qiu, Hu Xu, Chun Li, Jianfeng Xu
SkillLift introduces a method for efficiently evolving reusable procedural prompts (skills) in large language model agents by learning a dense rubric that aligns with sparse oracle evaluations. Instead of directly revising skill text based on costly full agent rollouts, the approach decouples skill search from oracle cost through a bilevel optimization framework: an inner loop uses a frozen rubric as a cheap surrogate to guide skill updates, while an outer loop periodically realigns the rubric using a small number of oracle rollouts via rank correlation. Experiments on complex agent task benchmarks demonstrate that SkillLift outperforms existing auto-skill methods while reducing token cost by 40–70% compared to frontier-evolving approaches.
By Haoxiang Kang, Ming Wen