Open machine learning engineering tasks require agents to interpret data, build models, debug code, and produce valid competition submissions. Although current coding agents can generate runnable programs, they often rediscover solutions across tasks and repeat engineering mistakes across feedback rounds. We propose EEMA, an experience-evolving meta-agent framework that organizes accumulated experience by purpose and routes it during multi-round solving. Its static component distills public competition material and historical failure traces into compact Skills: task-level modeling priors for improving solution quality and failure-prevention contracts for maintaining execution validity. Its dynamic component, Experience Routed Search (ERS), operates above a lower-level coding agent. At each round, ERS selects a draft, debug, or improve action, routes the corresponding Skill, and updates task memory, allowing cross-task experience to guide code generation while task-level feedback shapes later decisions. On MLE-bench Lite (22 tasks), EEMA achieves a 77.3% medal rate, 20.1% average leaderboard Grade, and 96.0% execution success, outperforming all baselines including GPT-5.5-xhigh. Ablations show that task Skills improve solution quality, failure-prevention Skills improve reliability, and ERS coordinates both effectively. The materials will be released at https://github.com/FrontisAI/OpenRSI.

Enterprise agents increasingly operate in workspaces, read heterogeneous files, use tools, and deliver business artifacts. We introduce EnterpriseClawBench, an internal enterprise agent benchmark constructed from proprietary agent sessions. Starting from a large archive of real workplace sessions, the EnterpriseClawBench pipeline produces 852 reproducible tasks with recovered fixtures, rewritten prompts, role classes, skill subclasses, hard rules, and semantic rubrics. Because the data contain internal enterprise content, the benchmark data are not released; the reusable contribution is the construction and evaluation protocol. On a manually audited 120-task Lite subset, the best score is only 0.663 for Codex with GPT-5.5. The results show that enterprise agent evaluation must report harness–model combinations, artifact delivery, visual quality, cost, runtime, and skill-transfer behavior rather than a single score.

Reinforcement learning (RL) paradigms have demonstrated strong performance on reasoning-intensive tasks such as code generation. However, limited trajectory diversity often leads to diminishing returns, which constrains the achievable performance ceiling. Search-enhanced RL alleviates this issue by introducing structured exploration, which remains constrained by the single-agent policy priors. Meanwhile, leveraging multiple interacting policies can acquire more diverse exploratory signals, but existing approaches are typically decoupled from structured search. We propose MARS² (Multi-Agent Reinforced Tree-Search Scaling), a unified RL framework in which multiple independently-optimized agents collaborate within a shared tree-structured search environment. MARS² models the search tree as a learnable multi-agent interaction environment, enabling heterogeneous agents to collaboratively generate and refine candidate solutions within a shared search topology. To support effective learning, we introduce a path-level group advantage formulation based on tree-consistent reward shaping, which facilitates effective credit assignment across complex search trajectories. Experiments on code generation benchmarks show that MARS² consistently improves performance across diverse model combinations and training settings, demonstrating the effectiveness of coupling multi-agent collaboration with tree search for enhancing reinforcement learning. Our code is publicly available at https://github.com/TsinghuaC3I/MARTI.

Recent studies indicate that LLM-based Multi-Agent Systems (MAS) encounter scalability challenges in complex mathematical problem-solving or coding tasks, exhibiting issues such as inconsistent role adherence and ineffective inter-agent communication. Moreover, the performance advantages of LLM-based MAS over a single agent employing test-time scaling methods (e.g., majority voting) remain marginal. This raises a critical question: Can LLM-based MAS scale effectively to achieve performance comparable to standalone LLMs or even Large Reasoning Models (LRMs) under optimal test-time compute?In this paper, we conduct a preliminary investigation into the scalability of LLM-based MAS for scientific code generation. We propose a simple yet scalable two-player framework based on iterative critic-in-the-loop refinement. Our experiments demonstrate that a minimalist actor-critic framework based on DeepSeek-V3 can outperform DeepSeek-R1 under equivalent computational budgets. Surprisingly, more complex frameworks fail to yield significant gains. These findings corroborate recent insights into multi-agent system limitations and highlight the importance of scalable workflows for advancing scientific code generation.

Peer review is essential for scientific progress but faces growing challenges due to increasing submission volumes and reviewer fatigue. Existing automated review approaches struggle with factual accuracy, rating consistency, and analytical depth, often generating superficial or generic feedback lacking the insights characteristic of high-quality human reviews. We introduce ReviewRL, a reinforcement learning framework for generating comprehensive and factually grounded scientific paper reviews. Our approach combines: (1) an ArXiv-MCP retrieval-augmented context generation pipeline that incorporates relevant scientific literature, (2) supervised fine-tuning that establishes foundational reviewing capabilities, and (3) a reinforcement learning procedure with a composite reward function that jointly enhances review quality and rating accuracy. Experiments on ICLR 2025 papers demonstrate that ReviewRL significantly outperforms existing methods across both rule-based metrics and model-based quality assessments. ReviewRL establishes a foundational framework for RL-driven automatic critique generation in scientific discovery, demonstrating promising potential for future development in this domain. The implementation of ReviewRL will be released at GitHub.

Supervised Fine-Tuning (SFT) and Preference Optimization (PO) are key processes for aligning Language Models (LMs) with human preferences post pre-training. While SFT excels in efficiency and PO in effectiveness, they are often combined sequentially without integrating their optimization objectives. This approach ignores the opportunities to bridge their paradigm gap and take the strengths from both. In this paper, we interpret SFT and PO with two sub-processes — Preference Estimation and Transition Optimization — defined at token level within the Markov Decision Process (MDP). This modeling shows that SFT is only a special case of PO with inferior estimation and optimization. PO estimates the model’s preference by its entire generation, while SFT only scores model’s subsequent predicted tokens based on prior tokens from ground truth answer. These priors deviates from model’s distribution, hindering the preference estimation and transition optimization. Building on this view, we introduce Intuitive Fine-Tuning (IFT) to integrate SFT and PO into a single process. Through a temporal residual connection, IFT brings better estimation and optimization by capturing LMs’ intuitive sense of its entire answers. But it solely relies on a single policy and the same volume of non-preference-labeled data as SFT. Our experiments show that IFT performs comparably or even superiorly to SFT and some typical PO methods across several tasks, particularly those requires generation, reasoning, and fact-following abilities. An explainable Frozen Lake game further validates the effectiveness of IFT for getting competitive policy.

Underlying data distributions of natural language, programming code, and mathematical symbols vary vastly, presenting a complex challenge for large language models (LLMs) that strive to achieve high performance across all three domains simultaneously. Achieving a very high level of proficiency for an LLM within a specific domain often requires extensive training with relevant corpora, which is typically accompanied by a sacrifice in performance in other domains. In this paper, we aim to “play the dealt cards well” and propose to fuse models that are already highly-specialized directly. The proposed fusing framework, , consists of different distinct specialists that are already sufficiently trained on different domains (we mainly focus on language, coding, and mathematics in this paper). A token-level gating mechanism is introduced to blend the specialists’ outputs. A two-stage training strategy accompanied by balanced sampling is designed to ensure stability. To effectively train the fused model, we further construct a high-quality supervised instruction tuning dataset, , which includes text, code, and mathematical content. This dataset comprises approximately 300,000 instructions and covers a wide range of topics in each domain. Experiments show that our model could simultaneously achieve mastery of the three crucial domains.

Despite the promising performance of state space models (SSMs) in long sequence modeling, limitations still exist. Advanced SSMs like S5 and S6 (Mamba) in addressing non-uniform sampling, their recursive structures impede efficient SSM computation via convolution. To overcome compatibility limitations in parallel convolutional computation, this paper proposes a novel non-recursive non-uniform sample processing strategy. Theoretical analysis of SSMs through the lens of Event-Triggered Control (ETC) theory reveals the Non-Stable State (NSS) problem, where deviations from sampling point requirements lead to error transmission and accumulation, causing the divergence of the SSM’s hidden state. Our analysis further reveals that adjustments of input sequences with early memories can mitigate the NSS problem, achieving Sampling Step Adaptation (SSA).Building on this insight, we introduce a simple yet effective plug-and-play mechanism, State Memory Replay (SMR), which utilizes learnable memories to adjust the current state with multi-step information for generalization at sampling points different from those in the training data. This enables SSMs to stably model varying sampling points. Experiments on long-range modeling tasks in autoregressive language modeling and Long Range Arena demonstrate the general effectiveness of the SMR mechanism for a series of SSM models.

Improving the effectiveness and efficiency of large language models (LLMs) simultaneously is a critical yet challenging research goal. In this paper, we find that low-rank pre-training, normally considered as efficient methods that will compromise performance, can be scalably effective when reduced parameters are precisely targeted. Specifically, by applying low-dimensional module only to the attention layer — resolves this issue and enhances both effectiveness and efficiency. We refer to this structure as Low-dimensional Projected Attention (LPA) and provide an explanatory analysis. Through extensive experimentation at parameter scales of 130M, 370M, and scaling up to 3B, we have validated the effectiveness and scalability of LPA. Our results show that LPA model can save up to 12.4% in time while achieving an approximate 5% improvement in test perplexity (ppl) and on downstream tasks compared with vanilla Transformer.