GRASP is a multi-stage planning framework that separates planning into specialized modules: GenPlan for global macro-guidelines, RevPlan for exploring localized strategies, and VerPlan for multi-criteria evaluation. This strategy-aware approach yields state‑of‑the‑art accuracy on diverse datasets, outperforming direct LLM planners by up to 30.8% on ZebraLogic and reducing multi‑task degradation. GRASP’s context isolation and macro‑regularization also give it a 14.5% edge over frontier reasoning models like GPT‑5‑mini.
arXiv:2609.14138v1 Announce Type: cross
Abstract: As LLM agents become integrated into increasingly complex workflows, they must continually acquire new capabilities while retaining competence on pre...
By Siddharth Sharma, Nilesh Prasad Pandey, Onat Gungor, Tajana Rosing
The paper introduces HiMA-Ecom, a hierarchical multi‑agent e‑commerce benchmark with 22.8K instances, where 17.7K include memory entries. It explores training, evaluation, and management of accumulated context in long‑horizon agentic systems, and proposes HiMA‑R1, a policy optimization method that controls trajectory context budgets and uses reward‑driven memory to accelerate convergence. Experiments show that agents built on 3B and 7B open‑source models outperform DeepSeek‑V3 by an average of 6.0 points, while reward‑driven memory cuts convergence steps by about 55%.
By Junxing Hu, Ai Han, Haolan Zhan, Pu Wei, Zhiqian Zhang, Yuhang Guo, Jiawei Lu, Zhen Chen, Haoran Li, Zicheng Zhang, Ling Li
arXiv:2610.14913v1 Announce Type: new
Abstract: Reinforcement learning (RL) is essential for adaptive decision-making, e.g., robust Meta-RL and domain randomization (DR), and efficient post-training...
By Jiarong Wen, Qi Tao, Kaiyu Zhang, Yun Qu, Lizhou Cai, Heming Zou, Yuhang Jiang, Qi Wang
arXiv:2510. 05592v2 Announce Type: replace Abstract: Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios.
By Zhuofeng Li, Haoxiang Zhang, Seungju Han, Sheng Liu, Jianwen Xie, Yu Zhang, Yejin Choi, James Zou, Pan Lu
FOCUS is a reinforcement learning method designed to improve long‑horizon language‑model agents by using selective branching to train a critic network more accurately. The rollout controller actively samples continuations from states that are expected to reduce the critic’s estimation error, and the refined value estimates are used to score segments between consecutive states with a TD(λ) advantage. Experiments on legal reasoning, deep search, and code localization tasks show that FOCUS outperforms baselines such as GRPO and VinePPO, achieving significant accuracy gains on benchmarks like BrowseComp‑Plus and DeonticBench.
By Zhengping Jiang, William Jurayj, Liaoyaqi Wang, Chunsheng Zuo, Anqi Liu, Benjamin Van Durme
arXiv:2604. 05164v3 Announce Type: replace-cross Abstract: As LLM reasoning performance plateaus, improving inference-time compute efficiency is crucial to mitigate overthinking and long thinking traces even for simple queries.
By Neharika Jali, Anupam Nayak, Gauri Joshi
GRASP is a multi-stage planning framework that improves the reliability of large language models on complex tasks. It separates planning into three specialized modules—GenPlan for global macro-guidelines, RevPlan for exploring localized strategies, and VerPlan for multi-criteria evaluation—allowing context isolation and strict macro-regularization. Experiments show GRASP outperforms direct LLM planners by significant margins on datasets such as Natural Plan Calendar Scheduling, ZebraLogic, and SciBench Math, and it mitigates performance collapse in multi-task and dual-task settings.
By Arunabh Srivastava (Amir), Mohammad A. (Amir), Khojastepour, Srimat Chakradhar, Sennur Ulukus
arXiv:2604. 17267v2 Announce Type: replace Abstract: Large Language Models can generate synthetic survey responses at low cost, but their accuracy varies unpredictably across questions.
By Zikun Ye, Hema Yoganarasimhan
The paper introduces PORA, a method that teaches large language model agents to decide when to allocate more reasoning steps versus fewer, based on the expected downstream benefit. PORA trains by running each state twice—once with short reasoning and once with long reasoning—and learns to predict the value of extended reasoning. During inference, a controller uses this prediction and remaining budget information to choose the appropriate reasoning length without running both options, improving performance across diverse tasks.
By Bo Yan, Qi Zhang, Zhen Tan, Tianlong Chen, Song Wang
arXiv:2607. 17545v1 Announce Type: new Abstract: Language agents depend on memory across interactions.
By Qingcan Kang, Mingyang Liu, Shixiong Kai, Kaichao Liang, Zhentao Tang, Yuqi Cui, Tao Zhong, Mingxuan Yuan
The paper proposes a method for allocating limited counterfactual annotation resources from multiple sources—such as domain experts and large language models—to improve off-policy evaluation in contextual bandits. By formulating an integer optimization problem that balances source-specific costs and error rates, the authors derive a majorization‑minimization algorithm that iteratively reduces estimator variance. Experiments on synthetic clinical and education bandit data demonstrate that the optimized allocation cuts mean‑squared error by over 20% compared to no annotation.
By Biao Xiang, Ali Eshragh, Yuexing Li, Kai Wang