This work proposes DART-SD (Diamond-topology Aware Retrieval and Tuning for Self-Distillation), a novel framework that shifts the paradigm from global forcing to topology-guided localized correction, and significantly outperforms traditional full-trajectory baselines.
Abstract
Equipping Large Language Models (LLMs) with multi-turn tool-calling capabilities is essential for building autonomous agents. However, progress is fundamentally limited by the reliance on full-length trajectory imitation. For tasks involving multiple order-independent sub-goals, the optimal solution space forms a vast combinatorial diamond lattice. Forcing this rich topology into monolithic trajectories causes a severe topological collapse, indiscriminately penalizing valid alternative explorations and severely degrading policy diversity. To address this, we propose DART-SD (Diamond-topology Aware Retrieval and Tuning for Self-Distillation), a novel framework that shifts the paradigm from global forcing to topology-guided localized correction. DART-SD first models the execution process as a converging Interaction-State Transition Graph (ISTG), faithfully capturing the inherent diamond topology of successful and failed exploratory paths. During autonomous rollouts, the framework identifies the Critical Topological Breakpoint (CTB) and retrieves success-supported recovery references. Finally, we introduce a progressive self-distillation paradigm through CTB-guided localized supervision, ensuring that the training loss is calculated exclusively on the generated recovery steps while strictly protecting the valid reasoning prefix from destructive gradient updates. Experiments on complex multi-turn tool-calling benchmarks demonstrate that DART-SD significantly outperforms traditional full-trajectory baselines.
Large language model (LLM)-based web search agents have demonstrated remarkable capabilities in autonomous information retrieval and multi-step reasoning. However, their robustness under real-world distribution shifts, such as evolving webpage structures, dynamic content layouts, and unseen task environments, remains a critical open challenge. Existing approaches predominantly rely on static supervised fine-tuning with human-annotated trajectories, which not only incurs substantial labeling cost but also lacks the adaptive capacity to handle the inherent stochasticity of live web environments. In this paper, we propose TAPE (Trajectory Alignment and exPerience pool Evolution), a novel self-evolving fine-tuning framework designed to enhance the generalization and robustness of web search agents without requiring large-scale human annotation. TAPE introduces a dual-stream experience pool that continuously accumulates both successful and failed agent trajectories during self-play execution. A trajectory alignment module maps heterogeneous execution paths into a unified semantic space, enabling contrastive learning to identify failure-inducing operations and reward generalizable search strategies. The framework further incorporates an adaptive pool evolution mechanism that filters, reweights, and distills experiences to prevent knowledge stagnation and distributional collapse. Extensive experiments on the GAIA benchmark and BrowseComp dataset demonstrate that TAPE consistently outperforms strong baselines across all three difficulty levels, achieving up to 6.2% absolute improvement in task success rate on GAIA Level-2 tasks (a 134.8% relative gain over the SFT-Only baseline on the GAIA validation split) and 1.3% absolute (217% relative) improvement on BrowseComp hard-tier queries, while exhibiting significantly greater resilience to webpage structure perturbations. These improvements are consistent across three open base models spanning two model families and the 7B–14B scale range. Our analysis further suggests that the contrastive self-play signal can serve as a useful partial surrogate for human preference labeling in agent trajectory optimization, substantially reducing, though not eliminating, reliance on human-annotated trajectories.
Minjae Rhee, Jitong Zou, Tianjun Mo et al.· IEEE Access· 0 citations
AgentKGV, the Agentic LLM-RAG framework for KG fact Verification, is proposed, that integrates dynamic routing and iterative query rewriting, which handles surface-form mismatch in document-level retrieval.
Yumin Heo, Hyeoncheol Lee, Sumin Seo et al.· 0 citations
DualLane, a novel parallel dual-path planning architecture designed for AI agents, adaptively manages the highly skewed frequency distribution characteristic of real-world user queries and underscores the practical viability and effectiveness of adaptive dual-path planning in large-scale, interactive AIOps systems.
Haoyu Wang, Wenxuan Ma, Bing Hu et al.· Proceedings of the 32nd ACM...· 0 citations
Training tool-use agents to improve from their own experience remains challenging, as supervised fine-tuning relies on fixed teacher-distilled trajectories, while sparse-reward reinforcement learning provides weak supervision for long-horizon interactions. We present DeepSearch-Evolve, a self-distillation framework for web agents built on DeepSearch-World, a deterministic and verifiable environment with reproducible search and page-reading tools. DeepSearch-World contains 420K multi-hop QA tasks constructed from entity-level random walks and supports key agentic cognitive behaviors useful for self-evolving, including progress verification, grounded reflection, and failure recovery. DeepSearch-Evolve iteratively performs trajectory generation, filtering, data mixing, and fine-tuning to train stronger agents. Without distillation from more capable models, DeepSearch-World-9B achieves competitive performance compared with open-source agents, reaching 31.2% on BrowseComp, 61.5% on GAIA, and 93.4% on HotpotQA, showing that verifiable environments enable scalable self-evolution for long-horizon web agents. We will release the environment, 420K training pool, validation set, model, and code to facilitate future research on self-improving deep search agents.
Xinyu Geng, Xuanhua He, Sixiang Chen et al.· 1 citation
At every re-observation point in a hierarchical Vision-Language-Action (VLA) system, two interface decisions must be made: when to terminate the current subtask and how far to execute the proposed action chunk. These decisions are mutually dependent---the optimal stopping point depends on what the executor plans to do, while the optimal execution length depends on where the subtask boundary lies---yet existing architectures evaluate them in isolation, an asymmetry neither module can overcome alone. We present SparkVLA, a stop-aware hierarchical VLA that resolves this mutual dependency by formulating both decisions as a single ranking: Stop competes against every action-prefix length in a unified candidate set, and the system selects the highest-scoring option, eliminating threshold tuning and requiring only offline ordinal preferences. An Anchor-Conditioned Context Encoding module caches a history-aware subtask anchor encoding onset-state memory and goal semantics, guiding visual-token pruning toward task-relevant regions; a Stop-Aware Action-Prefix Selection head scores all candidates via full self bnattention at chunk boundaries for efficiency. On RoboCerebra, SparkVLA achieves 47.12% success rate, surpassing the official hierarchical baseline by 30.57% and the strongest reproducible method by 26.83% Real-robot experiments on multi-step tasks further validate these gains on physical hardware.
Xunyao Lei, Renjun Wu, Tianlin Huo et al.· 0 citations
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
