arXiv AI September 25, 2026 By Xingyu Wu, Yuchen Yan, Zhengxi Lu, Siqi Chen, Xin ZHANG, Aiting Liu, Chao Deng, Jie Liu, Jin Ma, Jian Shao, Jun Xiao, Yongliang Shen

IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis

Read the original on arXiv AI →

IterSynth introduces a role-decoupled, iterative synthesis framework for deep search agents, separating planning and synthesis into distinct Planner and Synthesizer modules that maintain a persistent summary state. This design mitigates role coupling and context noise, while the new Role-Decoupled Policy Optimization (RDPO) enhances training by combining outcome rewards with turn-level rubric evaluations. Experiments on five long-horizon benchmarks show IterSynth-8B outperforming prior ≤8B agents by 4.2% and delivering significant zero-shot gains over ReAct on proprietary models.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

Aug 17

TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents

Long-horizon large language model (LLM) agents are typically optimized with sparse terminal outcomes, making fine-grained credit assignment across multi-step interactions difficult. Existing approache...

llms agents reinforcement-learning benchmarks

arXiv AI

Jun 10

HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning

arXiv:2606. 10507v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents across a wide range of tasks, their performance often degrades in multi-turn long-horizon agentic tasks.

By Juncheng Diao, Zhicong Lu, Peiguang Li, Yongwei Zhou, Changyuan Tian, Qingbin Li, Rongxiang Weng, Jingang Wang, Xunliang Cai

llms agents nlp reinforcement-learning benchmarks

arXiv AI

Aug 3

AttriMem: Attribution-Guided Process Feedback for Agent Memory Construction

arXiv:2607. 21106v2 Announce Type: replace Abstract: Effective memory is crucial for LLM agents, yet constructing it effectively remains challenging.

By Qinfeng Li, Yuntai Bao, Xinyan Yu, Hongze Chen, Yanmin Liu, Wenqi Zhang, Xuhong Zhang

llms agents nlp reinforcement-learning benchmarks

arXiv AI

Jul 24

AttriMem: Attribution-Guided Process Feedback for Agent Memory Learning

arXiv:2607. 21106v1 Announce Type: new Abstract: Effective memory is crucial for LLM agents, yet constructing it effectively remains challenging.

By Qinfeng Li, Yuntai Bao, Xinyan Yu, Hongze Chen, Wenqi Zhang, Xuhong Zhang

llms agents nlp reinforcement-learning benchmarks

arXiv AI

Jun 10

Divide and Cooperate: Role-Decomposed Multi-Agent LLM Training with Cross-Agent Learning Signals

arXiv:2606. 10684v1 Announce Type: cross Abstract: Modern language agents which perform multi-step reasoning have shown strong performance in knowledge-intensive question answering.

By Jaewan Park, Solbee Cho, Jay-Yoon Lee

llms agents nlp fine-tuning benchmarks

arXiv AI

Aug 14

Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents

arXiv:2608. 12764v1 Announce Type: cross Abstract: Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sparse for effective credit assignment.

By Haoze Wu, Chuqiao Kuang, Tianyi Zhuang, Xiaoguang Li

agents reinforcement-learning efficiency

One email a morning, machine-written

Related stories

TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents

HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning

AttriMem: Attribution-Guided Process Feedback for Agent Memory Construction

AttriMem: Attribution-Guided Process Feedback for Agent Memory Learning

Divide and Cooperate: Role-Decomposed Multi-Agent LLM Training with Cross-Agent Learning Signals

Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents