Weihao Xie

Zhen Chen, Yibing Liu, Weihao Xie et al.

Retrieval-augmented generation (RAG) systems expose numerous design choices spanning query rewriting, chunking, retrieval depth, reranking, and context compression. In practice, these choices are often configured through heuristics, hindering systematic evaluation and reproducibility across settings. We argue that this challenge is best formulated as RAG architecture search. To support controlled and reproducible study of this problem, we introduce the RAG Intelligence Search Engine (RAISE), a comprehensive framework and benchmark for RAG hyperparameter optimization, which evaluates optimization methods for RAG pipelines under standardized search spaces and budgets. RAISE implements 13 search algorithms and evaluates them across seven public text and multimodal datasets using three random seeds. Our experiments show that optimization performance is highly task-dependent: methods that perform strongly on one dataset may not generalize consistently across others, cautioning against interpreting aggregate rankings as evidence of universally superior strategies. RAISE provides a common experimental substrate for fair, reproducible, and systematic research on RAG hyperparameter optimization.

Ailin Huang, Ang Li, Aobo Kong et al.

We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most when building agents: sharp reasoning and fast, reliable execution. Step 3.5 Flash pairs a 196B-parameter foundation with 11B active parameters for efficient inference. It is optimized with interleaved 3:1 sliding-window/full attention and Multi-Token Prediction (MTP-3) to reduce the latency and cost of multi-round agentic interactions. To reach frontier-level intelligence, we design a scalable reinforcement learning framework that combines verifiable signals with preference feedback, while remaining stable under large-scale off-policy training, enabling consistent self-improvement across mathematics, code, and tool use. Step 3.5 Flash demonstrates strong performance across agent, coding, and math tasks, achieving 85.4% on IMO-AnswerBench, 86.4% on LiveCodeBench-v6 (2024.08-2025.05), 88.2% on tau2-Bench, 69.0% on BrowseComp (with context management), and 51.0% on Terminal-Bench 2.0, comparable to frontier models such as GPT-5.2 xHigh and Gemini 3.0 Pro. By redefining the efficiency frontier, Step 3.5 Flash provides a high-density foundation for deploying sophisticated agents in real-world industrial environments.

Dingling Zhang, He Zhu, Jincheng Ren et al.

Deep Research Agents (DRAs) aim to automatically produce analyst-level reports through iterative information retrieval and synthesis. However, most existing DRAs were validated on question-answering benchmarks, while research on generating comprehensive reports remains overlooked. Worse, current benchmarks for report synthesis suffer from task complexity and subjective metrics -- this fails to reflect user demands and limits the practical utility of generated reports. To address these gaps, we present Fine-grained DEepResearch bench (FINDER), an enhanced benchmark consisting of 100 human-curated research tasks with 419 structured checklist items that standardize report structure, analytical depth, and factual grounding. Based on approximately 1,000 reports produced by mainstream DRAs, we further propose Deep rEsearch Failure Taxonomy (DEFT), the first failure taxonomy for deep research agents. DEFT contains 14 fine-grained failure modes across reasoning, retrieval, and generation, and is built upon grounded theory with human-LLM co-annotating and inter-annotator reliability validation. Our experimental findings reveal that current DRAs struggle not with task comprehension but with evidence integration, verification, and reasoning-resilient planning.

Caorui Li, Yu Chen, Yiyan Ji et al. · pku

Recent advances in multimodal large language models (MLLMs) have demonstrated substantial potential in video understanding. However, existing benchmarks fail to comprehensively evaluate synergistic reasoning capabilities across audio and visual modalities, often neglecting either one of the modalities or integrating them in a logically inconsistent manner. To bridge this gap, we introduce OmniVideoBench, a large-scale and rigorously designed benchmark dedicated to assessing synergistic audio-visual understanding, with a strong emphasis on modality complementarity and logical consistency. Specifically, OmniVideoBench comprises 1000 high-quality question-answer(QA) pairs, each annotated with step-by-step reasoning traces, derived from 628 diverse videos ranging from several seconds to 30 minutes, and manually verified to guarantee complete correctness and uniqueness. Moreover, OmniVideoBench encompasses 13 carefully designed question types, covering temporal reasoning, spatial localization, counting, causal inference, summarization, and beyond, thereby capturing the essential challenges of video understanding. Evaluation of multiple MLLMs on OmniVideoBench reveals a pronounced gap between model performance and human reasoning, with open-source models lagging significantly behind their closed-source counterparts, underscoring the inherent difficulty of genuine audio-visual reasoning. We will release OmniVideoBench to foster the development of MLLMs with stronger and more generalizable reasoning capabilities.

Han Li, Jinyu Tian, Rili Feng et al.

Large language models (LLMs) still struggle with the rigorous reasoning demands of hard competitive programming. While recent multi-agent frameworks attempt to bridge this reliability gap, they remain fundamentally stateless: they rely on static retrieval and discard the valuable problem-solving and debugging experience gained from previous tasks. To address this, we present Solvita, an agentic evolution framework that enables continuous learning without requiring weight updates to the underlying LLM. Solvita reorganizes problem-solving into a closed-loop system of strategy selection, program synthesis, certified supervision, and targeted hacking, executed by four specialized agents: Planner, Solver, Oracle, and Hacker. Crucially, each agent is paired with a trainable, graph-structured knowledge network. As the system operates, outcome signals, such as pass/fail verdicts, test certification quality, and adversarial vulnerabilities discovered by the Hacker, are recast as reinforcement learning updates to these network weights. This allows the agents to dynamically route future queries based on past successes and failures, effectively accumulating transferable reasoning experience over time. Evaluated across CodeContests, APPS, AetherCode, and live Codeforces rounds, Solvita establishes a new state-of-the-art among code-generation agents, outperforming existing multi-agent pipelines and nearly doubling the accuracy of single-pass baselines.

Zhen Chen, Weihao Xie, Peilin Chen et al.

Retrieval-Augmented Generation (RAG) has proven effective for knowledge synthesis, yet it encounters significant challenges in practical scenarios where data is inherently discrete and fragmented. In most environments, information is distributed across isolated files like reports and logs that lack explicit links. Standard search engines process files independently, ignoring the connections between them. Furthermore, manually building Knowledge Graphs is impractical for such vast data. To bridge this gap, we present Orion-RAG. Our core insight is simple yet effective: we do not need heavy algorithms to organize this data. Instead, we use a low-complexity strategy to extract lightweight paths that naturally link related concepts. We demonstrate that this streamlined approach suffices to transform fragmented documents into semi-structured data, enabling the system to link information across different files effectively. Extensive experiments demonstrate that Orion-RAG consistently outperforms mainstream frameworks across diverse domains, supporting real-time updates and explicit Human-in-the-Loop verification with high cost-efficiency. Experiments on FinanceBench demonstrate superior precision with a 25.2% relative improvement over strong baselines.

Shihao Li, Yuanxing Zhang, Jiangtao Wu et al.

Although Multimodal Large Language Models (MLLMs) have demonstrated proficiency in video captioning, practical applications require captions that follow specific user instructions rather than generating exhaustive, unconstrained descriptions. Current benchmarks, however, primarily assess descriptive comprehensiveness while largely overlooking instruction-following capabilities. To address this gap, we introduce IF-VidCap, a new benchmark for evaluating controllable video captioning, which contains 1,400 high-quality samples. Distinct from existing video captioning or general instruction-following benchmarks, IF-VidCap incorporates a systematic framework that assesses captions on two dimensions: format correctness and content correctness. Our comprehensive evaluation of over 20 prominent models reveals a nuanced landscape: despite the continued dominance of proprietary models, the performance gap is closing, with top-tier open-source solutions now achieving near-parity. Furthermore, we find that models specialized for dense captioning underperform general-purpose MLLMs on complex instructions, indicating that future work should simultaneously advance both descriptive richness and instruction-following fidelity.

Ken Deng, Zizheng Zhan, Wen Xiang et al.

Large Language Models (LLMs) increasingly rely on Chain-of-Thought (CoT) reasoning to improve accuracy on complex tasks. However, always generating lengthy reasoning traces is inefficient, leading to excessive token usage and higher inference costs. This paper introduces the Hybrid Policy Optimization (i.e., HiPO), a framework for adaptive reasoning control that enables LLMs to selectively decide when to engage in detailed reasoning (Think-on) and when to respond directly (Think-off). Specifically, HiPO combines a hybrid data pipelineproviding paired Think-on and Think-off responseswith a hybrid reinforcement learning reward system that balances accuracy and efficiency while avoiding over-reliance on detailed reasoning. Experiments across mathematics and coding benchmarks demonstrate that HiPO can substantially reduce token length while maintaining or improving accuracy. Finally, we hope HiPO a can be a principled approach for efficient adaptive reasoning, advancing the deployment of reasoning-oriented LLMs in real-world, resource-sensitive settings.

Jingzhe Ding, Shengda Long, Changxin Pu et al.

Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks fail to rigorously evaluate the long-horizon capabilities required to build complete software systems. Most prior evaluations focus on localized code generation, scaffolded completion, or short-term repair tasks, leaving open the question of whether agents can sustain coherent reasoning, planning, and execution over the extended horizons demanded by real-world repository construction. To address this gap, we present NL2Repo Bench, a benchmark explicitly designed to evaluate the long-horizon repository generation ability of coding agents. Given only a single natural-language requirements document and an empty workspace, agents must autonomously design the architecture, manage dependencies, implement multi-module logic, and produce a fully installable Python library. Our experiments across state-of-the-art open- and closed-source models reveal that long-horizon repository generation remains largely unsolved: even the strongest agents achieve below 40% average test pass rates and rarely complete an entire repository correctly. Detailed analysis uncovers fundamental long-horizon failure modes, including premature termination, loss of global coherence, fragile cross-file dependencies, and inadequate planning over hundreds of interaction steps. NL2Repo Bench establishes a rigorous, verifiable testbed for measuring sustained agentic competence and highlights long-horizon reasoning as a central bottleneck for the next generation of autonomous coding agents.

Chris Xing Tian, Weihao Xie, Zhen Chen et al.

Retrieval-Augmented Generation (RAG) combines the language understanding and reasoning power of large language models (LLMs) with external retrieval to enable domain-grounded responses. Effectively adapting RAG systems to domain-specific settings requires specialized, context-rich training data beyond general-purpose question-answering. Here, we propose RAGen, a scalable and modular framework for generating domain-grounded question-answer-context (QAC) triples tailored to diverse RAG adaptation approaches. RAGen produces these QAC triples by identifying key concepts in documents, generating diverse questions guided by Bloom's Taxonomy-inspired principles, and pairing them with precise answers extracted from relevant contexts. RAGen supports multiple RAG adaptation strategies, including the optimization of key components such as the LLM, retriever, and embedding model, etc. Its modular pipeline features semantic chunking, hierarchical concept extraction, and multi-chunk retrieval, along with the introduction of curated distractor contexts to promote robust reasoning. Designed for scalability, RAGen efficiently handles large and evolving document corpora without redundant processing, making it especially suitable for dynamic evolving domains such as scientific research and enterprise knowledge bases.

Yuqi Jin, Zhenhao Shuai, Zihan Hu et al.

Background and Aims: Large language models (LLMs) have shown remarkable generalization and transfer capabilities by learning from vast corpora of text and web data. Their semantic representations allow cross-task knowledge transfer and reasoning, offering promising opportunities for data-scarce and heterogeneous domains such as clinical medicine. Yet, in diagnostic tasks like sarcopenia, major challenges remain: interpretability, transparency, and deployment efficiency. Traditional machine learning (TML) models provide stable performance and feature-level attribution, ensuring traceable and auditable decision logic, but lack semantic breadth. Conversely, LLMs enable flexible inference but often function as opaque predictors. Existing integration strategies remain shallow, rarely embedding the structured reasoning of TML into LLM inference. Methods: Using sarcopenia diagnosis as a case study, SHapley Additive exPlanations (SHAP) were extracted from a baseline XGBoost model and transformed into structured, LLM-compatible representations. An actor-critic reinforcement learning (RL) strategy guided the LLM to reason over these SHAP-based inputs, producing calibrated rationales and refined decision rules. The distilled reasoning was consolidated into a structured knowledge repository and deployed via retrieval-augmented generation (RAG) for case-based inference. Results: (Omitted here.) Conclusion: By coupling SHAP-derived statistical evidence with reinforcement-trained LLM reasoning, CANDLE mitigates the interpretability-performance trade-off, enhances predictive accuracy, and preserves high decision consistency. The framework offers a scalable approach to knowledge assetization of TML models, enabling interpretable, reproducible, and clinically aligned decision support in sarcopenia and potentially broader medical domains.