Traverse: Learning When to Remember, Reset, and Redirect for Long-Horizon Web Search

arXiv:2609.37082 · cs.CL · Submitted 2026-09-29 · Read on arXiv

cs.CL

Submitted: 2026-09-29

Updated: 2026-09-30

Code: https://github.com/ByteDance-BandAI/Traversehuggingface.co

Terminology

• Benchmark — 23× in this paper · explained in 2 episodes
• Accuracy — 15× in this paper · explained in 1 episode
• Verification — 15× in this paper · explained in 2 episodes
• Reinforcement Learning — 8× in this paper · explained in 4 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Verifier — 7× in this paper · explained in 2 episodes
• Credit assignment — 4× in this paper · explained in 3 episodes
• Knowledge Graph — 4× in this paper · explained in 7 episodes
• Ablation Studies — 3× in this paper · explained in 1 episode
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Calibration — 2× in this paper · explained in 7 episodes
• GRPO — 2× in this paper · explained in 6 episodes
• Satisfaction of Products — 2× in this paper
• Agent Harness — 1× in this paper · explained in 2 episodes
• Agentic Search — 1× in this paper · explained in 1 episode
• Agentic Task — 1× in this paper · explained in 1 episode
• Agentic Tasks — 1× in this paper · explained in 1 episode
• Commentary — 1× in this paper · explained in 2 episodes
• Knowledge graphs — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• IterResearch: Rethinking Long-Horizon Agents with Interaction Scaling
• ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• GLM-5: from Vibe Coding to Agentic Engineering
• DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents
• FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• WebSailor: Navigating Super-human Reasoning for Web Agent
• AREX: Towards a Recursively Self-Improving Agent for Deep Research
• DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
• WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization
• Kimi K3: Open Frontier Intelligence
• ShoppingComp: Are LLMs Really Ready for Your Shopping Cart?
• BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents
• WideSearch: Benchmarking Agentic Broad Info-Seeking
• ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
• QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks
• Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
• Group Sequence Policy Optimization

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering