Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910129805328384 |
|---|---|
| author | Mo, Fengran Gao, Yifan Li, Sha Zeng, Hansi Liu, Xin Tan, Zhaoxuan Li, Xian Chen, Jianshu Wang, Dakuo Jiang, Meng |
| author_facet | Mo, Fengran Gao, Yifan Li, Sha Zeng, Hansi Liu, Xin Tan, Zhaoxuan Li, Xian Chen, Jianshu Wang, Dakuo Jiang, Meng |
| contents | Large Language Models (LLMs) have become a popular interface for human-AI interaction, supporting information seeking and task assistance through natural, multi-turn dialogue. To respond to users within multi-turn dialogues, the context-dependent user intent evolves across interactions, requiring contextual interpretation, query reformulation, and dynamic coordination between retrieval and generation. Existing studies usually follow static rewrite, retrieve, and generate pipelines, which optimize different procedures separately and overlook the mixed-initiative action optimization simultaneously. Although the recent developments in deep search agents demonstrate the effectiveness in jointly optimizing retrieval and generation via reasoning, these approaches focus on single-turn scenarios, which might lack the ability to handle multi-turn interactions. We introduce a conversational agent that interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through reinforcement learning (RL) training with tailored rewards towards evolving user goals. The experimental results across four widely used conversational benchmarks demonstrate the effectiveness of our methods by surpassing several existing strong baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_13115 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning Mo, Fengran Gao, Yifan Li, Sha Zeng, Hansi Liu, Xin Tan, Zhaoxuan Li, Xian Chen, Jianshu Wang, Dakuo Jiang, Meng Computation and Language Information Retrieval Large Language Models (LLMs) have become a popular interface for human-AI interaction, supporting information seeking and task assistance through natural, multi-turn dialogue. To respond to users within multi-turn dialogues, the context-dependent user intent evolves across interactions, requiring contextual interpretation, query reformulation, and dynamic coordination between retrieval and generation. Existing studies usually follow static rewrite, retrieve, and generate pipelines, which optimize different procedures separately and overlook the mixed-initiative action optimization simultaneously. Although the recent developments in deep search agents demonstrate the effectiveness in jointly optimizing retrieval and generation via reasoning, these approaches focus on single-turn scenarios, which might lack the ability to handle multi-turn interactions. We introduce a conversational agent that interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through reinforcement learning (RL) training with tailored rewards towards evolving user goals. The experimental results across four widely used conversational benchmarks demonstrate the effectiveness of our methods by surpassing several existing strong baselines. |
| title | Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2601.13115 |