WebDancer: Towards Autonomous Information Seeking Agency

Addressing intricate real-world problems necessitates in-depth information seeking and multi-step reasoning. Recent progress in agentic systems, exemplified by Deep Research, underscores the potential for autonomous multi-step research. In this work, we present a cohesive paradigm for building end-to-end agentic information seeking agents from a data-centric and training-stage perspective. Our approach consists of four key stages: (1) browsing data construction, (2) trajectories sampling, (3) supervised fine-tuning for effective cold start, and (4) reinforcement learning for enhanced generalisation. We instantiate this framework in a web agent based on the ReAct, WebDancer. Empirical evaluations on the challenging information seeking benchmarks, GAIA and WebWalkerQA, demonstrate the strong performance of WebDancer, achieving considerable results and highlighting the efficacy of our training paradigm. Further analysis of agent training provides valuable insights and actionable, systematic pathways for developing more capable agentic models. The codes and demo will be released in https://github.com/Alibaba-NLP/WebAgent.

EvolveSearch: An Iterative Self-Evolving Search Agent

The rapid advancement of large language models (LLMs) has transformed the landscape of agentic information seeking capabilities through the integration of tools such as search engines and web browsers. However, current mainstream approaches for enabling LLM web search proficiency face significant challenges: supervised fine-tuning struggles with data production in open-search domains, while RL converges quickly, limiting their data utilization efficiency. To address these issues, we propose EvolveSearch, a novel iterative self-evolution framework that combines SFT and RL to enhance agentic web search capabilities without any external human-annotated reasoning data. Extensive experiments on seven multi-hop question-answering (MHQA) benchmarks demonstrate that EvolveSearch consistently improves performance across iterations, ultimately achieving an average improvement of 4.7\% over the current state-of-the-art across seven benchmarks, opening the door to self-evolution agentic capabilities in open web search domains.

Unlocking the Non-Native Language Context Limitation: Native Language Prompting Facilitates Knowledge Elicitation

Multilingual large language models (MLLMs) struggle to answer questions posed in non-dominant languages, even though they have already acquired the relevant knowledge from their dominant language corpus. In contrast, human multilinguals can overcome this issue by invoking the relatively rich knowledge acquired from native language texts through Positive Native Language Transfer (PNLT). Inspired by this, we analogize the dominant language of MLLMs to the native language of human multilinguals, and propose Native Language Prompting (NatLan) to simulate the PNLT observed in human multilinguals. It explicitly creates native language contexts for MLLMs to facilitate the elicitation of the rich native language knowledge during question-answering, unlocking the limitations imposed by non-native language contexts on the effective application of knowledge. By employing multi-MLLM collaboration, NatLan reduces the workload on each MLLM in simulating PNLT and refines semantic transfer. On the C-Eval benchmark, NatLan provides up to a 10.1% average accuracy improvement and up to a 5.0% increase in the hard-level subset across five MLLMs, surpassing all top-notch related methods. Our code is available at https://github.com/AnonyNLP/NatLan.