arXiv:2602.17547v2 Announce Type: replace Abstract: This paper introduces KLong, an open-source LLM agent trained to solve extremely long-horizon tasks. The principle is to first cold-start the model via trajectory-splitting SFT, then scale it via progressive RL training. Specifically, we first activate basic agentic abilities of a base model with a comprehensive SFT recipe. Then, we introduce Research-Factory, an automated pipeline that generates high-quality training data by collecting research papers and constructing evaluation rubrics. Using this pipeline, we build thousands of long-horizon trajectories distilled from Claude 4.5 Sonnet (Thinking). To train with these extremely long trajectories, we propose a new trajectory-splitting SFT, which preserves early context, progressively truncates later context, and maintains overlap between sub-trajectories. In addition, to further improve long-horizon task-solving capability, we propose a novel progressive RL, which schedules training into multiple stages with progressively extended timeouts. Experiments demonstrate the superiority and generalization of KLong, as shown in Figure 1. Notably, our proposed KLong (106B) surpasses Kimi K2 Thinking (1T) by 11.28% on PaperBench, and the performance improvement generalizes to other coding benchmarks like SWE-bench Verified and MLE-bench.

arXiv:2603.03820v1 Announce Type: cross Abstract: Interactive recommender systems (IRS) are increasingly optimized with Reinforcement Learning (RL) to capture the sequential nature of user-system dynamics. However, existing fairness-aware methods often suffer from a fundamental oversight: they assume the observed user state is a faithful representation of true preferences. In reality, implicit feedback is contaminated by popularity-driven noise and exposure bias, creating a distorted state that misleads the RL agent. We argue that the persistent conflict between accuracy and fairness is not merely a reward-shaping issue, but a state estimation failure. In this work, we propose \textbf{DSRM-HRL}, a framework that reformulates fairness-aware recommendation as a latent state purification problem followed by decoupled hierarchical decision-making. We introduce a Denoising State Representation Module (DSRM) based on diffusion models to recover the low-entropy latent preference manifold from high-entropy, noisy interaction histories. Built upon this purified state, a Hierarchical Reinforcement Learning (HRL) agent is employed to decouple conflicting objectives: a high-level policy regulates long-term fairness trajectories, while a low-level policy optimizes short-term engagement under these dynamic constraints. Extensive experiments on high-fidelity simulators (KuaiRec, KuaiRand) demonstrate that DSRM-HRL effectively breaks the "rich-get-richer" feedback loop, achieving a superior Pareto frontier between recommendation utility and exposure equity.

arXiv:2603.03094v1 Announce Type: cross Abstract: Item-side fairness is crucial for ensuring the fair exposure of long-tail items in interactive recommender systems. Existing approaches promote the exposure of long-tail items by directly incorporating them into recommended results. This causes misalignment between user preferences and the recommended long-tail items, which hinders long-term user engagement and reduces the effectiveness of recommendations. We aim for a proactive fairness-guiding strategy, which actively guides user preferences toward long-tail items while preserving user satisfaction during the interactive recommendation process. To this end, we propose HRL4PFG, an interactive recommendation framework that leverages hierarchical reinforcement learning to guide user preferences toward long-tail items progressively. HRL4PFG operates through a macro-level process that generates fairness-guided targets based on multi-step feedback, and a micro-level process that fine-tunes recommendations in real time according to both these targets and evolving user preferences. Extensive experiments show that HRL4PFG improves cumulative interaction rewards and maximum user interaction length by a larger margin when compared with state-of-the-art methods in interactive recommendation environments.

arXiv:2602.18479v1 Announce Type: cross Abstract: This paper presents a large language model (LLM) agent named AgentCAT, which extracts and analyzes catalytic reaction data from chemical engineering papers, %and supports natural language based interactive analysis of the extracted data. AgentCAT serves as an alternative to overcome the long-standing data bottleneck in chemical engineering field, and its natural language based interactive data analysis functionality is friendly to the community. AgentCAT also presents a formal abstraction and challenge analysis of the catalytic reaction data extraction task in an artificial intelligence-friendly manner. This abstraction would help the artificial intelligence community understand this problem and in turn would attract more attention to address it. Technically, the complex catalytic process leads to complicated dependency structure in catalytic reaction data with respect to elementary reaction steps, molecular behaviors, measurement evidence, etc. This dependency structure makes it challenging to guarantee the correctness and completeness of data extraction, as well as representing them for analysis. AgentCAT addresses this challenge and it makes four folds of technical contributions: (1) a schema-governed extraction pipeline with progressive schema evolution, enabling robust data extraction from chemical engineering papers; (2) a dependency-aware reaction-network knowledge graph that links catalysts/active sites, synthesis-derived descriptors, mechanistic claims with evidence, and macroscopic outcomes, preserving process coupling and traceability; (3) a general querying module that supports natural-language exploration and visualization over the constructed graph for cross-paper analysis; (4) an evaluation on $\sim$800 peer-reviewed chemical engineering publications demonstrating the effectiveness of AgentCAT.