Historical experience can guide scientific coding at multiple levels, but task-level retrieval may miss implementation lessons that become relevant during execution. We introduce MUSE, a memory management framework combining multi-level memory with selective runtime injection for scientific coding agents. MUSE builds global, approach-level, and implementation-level memory from historical trajectories. At initialization, the agent receives global memory and problem-matched approach-level memory. During execution, current interactions are used to retrieve implementation-level memory. An LLM gate selects relevant experience and generates specific review advice, or skips injection. Across four benchmarks spanning numerical problem solving, kernel optimization, and scientific software repair, MUSE outperforms retrieval and memory baselines on all evaluation metrics. Ablations support the multi-level design and gated injection, while transfer experiments show that memory remains useful across kernel benchmarks. These results show that multi-level memory and selective runtime injection enable effective reuse of experience in scientific coding. Code is available at https://github.com/hr-jin/MUSE.
Meng Li, Lei Li Tencent, Xiting Wang Renmin University of China, Yi Yuan, Zheng Wei Tencent Technology (Beijing) Company Limited, Brucebian Tencent AI Lab, Zang Li Tencent
Agentic reinforcement learning enables large language models to solve long-horizon tasks by interacting with the environment and internalizing tool-use behavior into their reasoning. Prior work assigns supervision primarily based on outcome rewards or external reward models, but largely ignores environment observations, a critical source of learning. Consequently, agents may identify successful actions without understanding how the environment responds, producing suboptimal policies. To address this, we propose SOAR (Supervision from Observation for Agentic Reinforcement Learning), which assigns positive advantages to observation tokens proportional to the negative entropy of preceding actions. This encourages the agent to learn from outcomes of confident actions, grounding policy updates in environment dynamics and improving anticipation of tool-call consequences. Empirical results across three domains and 14 benchmarks show that SOAR improves performance, yielding gains of up to 7.0% on general reasoning tasks and 16.9% on deep research tasks, while reducing erroneous and inefficient tool usage.
尚无 AI 解读，展示原文摘要
cs.CL · cs.AI
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Yifan Gong, Jing Yao Microsoft, Xiting Wang Renmin University of China, Xunlong Wang Renmin University of China, Xiaoyuan Yi Microsoft Research, Xing Xie Microsoft Research Asia
Reinforcement Learning from Human Feedback (RLHF) has emerged as a crucial technique for aligning large language models (LLMs) with human preferences. However, existing RLHF methods face key challenges, including poor sample efficiency, high computational overhead, and slow convergence. Recent studies highlight the importance of data selection in RL, but how to effectively select the most beneficial experiences for RL training remains an open problem. Existing data selection methods for RL rely on heuristic metrics, failing to establish an interpretable connection between data and optimization objectives. To address this problem, we propose InfOES (Influence-based Online Experience Selection), a novel data selection method for RLHF that dynamically estimates the influence of individual training samples on policy optimization. By incorporating data attribution into the policy gradient, InfOES can identify and filter out detrimental samples on the fly, ensuring effective convergence toward alignment objectives. Our approach is compatible with various RL algorithms (e.g., PPO, GRPO, REINFORCE++). Extensive experiments demonstrate that InfOES significantly enhances training effectiveness, achieving superior alignment performance with fewer optimization steps.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Zhihao Xu, Fuzhen Yang, Liang Lin, Xiting Wang Renmin University of China
Recent advancements in Large Reasoning Models (LRMs) have showcased strong performance across various reasoning tasks by leveraging System-2 thinking capabilities. However, existing studies indicate that this reasoning ability alone does not reliably transfer to the general alignment domain. Inspired by cognitive science and how humans solve tasks, we argue that LRMs must be equipped with metacognitive knowledge to fully utilize their System-2 capabilities. In this paper, we propose Priority-Aware Metacognition (PAM), which guides the model to first identify the top-level human preference (e.g., harmlessness) as a means of understanding the alignment task’s nature, and then apply other kinds of metacognitive knowledge to better monitor and regulate the model’s thinking process. We implement PAM via a two-stage pipeline: a cold-start phase that collects structured metacognitive knowledge based on Flavell’s theoretical framework, and a preference-optimization phase that further reinforces such metacognition. Extensive experiments validate the effectiveness of PAM. Under the same training pipelines, PAM consistently yields higher performance, improving general domain alignment performance by ~10 points on the helpfulness and harmless benchmarks. Code is available at https://anonymous.4open.science/r/PAM-RM-02DF.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Zhihao Xu, Rumei Li Meituan, Jiahuan Li Meituan, Rongxiang Weng, Jingang Wang Meituan, Xunliang Cai Meituan, Xiting Wang Renmin University of China
Enabling Large Language Models (LLMs) to effectively utilize tools in multi-turn interactions is essential for building capable autonomous agents. However, acquiring diverse and realistic multi-turn tool-use data remains a significant challenge. In this work, we propose a novel text-based paradigm. We observe that textual corpora naturally contain rich, multi-step problem-solving experiences, which can serve as an untapped, scalable, and authentic data source for multi-turn tool-use tasks. Based on this insight, we introduce GEM, a data synthesis pipeline that enables the generation and extraction of multi-turn tool-use trajectories from text corpora through a four-stage process: relevance filtering, workflow tool extraction, trajectory grounding, and complexity refinement. To reduce the computational cost, we further train a specialized Trajectory Synthesizer via supervised fine-tuning. This model distills the complex generation pipeline into an efficient, end-to-end trajectory generator. Experiments demonstrate that our GEM-32B achieve a 14.9% improvement on the BFCL V3 Multi-turn benchmark. Our models partially surpass the performance of models trained on -bench (Airline and Retail) in-domain data, highlighting the superior generalization capability derived from our text-based synthesis paradigm. Notably, our Trajectory Synthesizer matches the quality of the full pipeline while significantly reducing inference latency and costs.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Qian Cao, Yahui Liu, Wei Bi Independent Researcher, Yi Zhao, Ruihua Song, Xiting Wang Renmin University of China, Ruiming Tang, Guorui Zhou Kuaishou- 快手科技 等 9 位作者
Reinforcement learning (RL)-based enhancement of large language models (LLMs) often leads to reduced output diversity, undermining their utility in open-ended tasks like creative writing. Current methods lack explicit mechanisms for guiding diverse exploration and instead prioritize optimization efficiency and performance over diversity. This paper proposes an RL framework structured around a semi-structured long Chain-of-Thought (CoT), in which the generation process is decomposed into explicitly planned intermediate steps. We introduce a Diverse Planning Branching method that strategically introduces divergence at the planning phase based on diversity variation, alongside a group-aware diversity reward to encourage distinct trajectories. Experimental results on creative writing benchmarks demonstrate that our approach significantly improves output diversity without compromising generation quality, consistently outperforming existing baselines.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表