The authors organize web search into three recurring states.
Agents learn to reset noisy context during long web searches
Traverse combines self-directed answer criteria, verification, and memory checkpoints with reinforcement learning designed to avoid unstable tool-use training.
Chinese Tech
Jingyuan Ma · Lynx Aster · He Zhang · Siyao Song · Weijie Yuan · Zhe Zhang · +2 more
State Key Laboratory of Multimedia Information Processing · Peking University · ByteDance
Research Digest··2 min read
Ma et al.
Why this paper
From ByteDance and 2 others · Part of Context Engineering for Agents, now 41 papers
In one line
A rubric-driven search agent with self-managed memory and answer verification reaches 72.83 on BrowseComp and improves across several other search tasks.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§