A trace records steps in a process. Keep each claim connected to its source.
Read the research question.
Locate the relevant figure or example.
Keep source links with your notes.
Record open questions for the next pass.
3. Keep code intact
for paper in reading_list:
print(paper["title"], paper["url"])
Illustrative reading checklist. Open each source for the complete paper.
# Three papers. Three research questions.
> **Sources:** [When Agents Slow Down](https://arxiv.org/abs/2609.15309) · [WearableQA](https://arxiv.org/abs/2609.05405) · [Conversation Compiler](https://arxiv.org/abs/2603.29678)
## 1. Start with the research question
1. **Agent reasoning**
- Inspect the test-time strategy and token budget.
- Follow the decisions recorded in the *trace*.
2. **Wearable data**
- Check the available health signals.
- Separate the task definition from the evidence.
3. **Conversation analysis**
- Follow the views used to inspect an agent trace.
- Return to the original paper for its full method.
### 1.1 A compact comparison
| Paper | Research focus | Read for |
| :--- | :--- | :--- |
| [When Agents Slow Down](https://arxiv.org/abs/2609.15309) | LLM agent strategies | Compute and progress |
| [WearableQA](https://arxiv.org/abs/2609.05405) | Reasoning over wearable data | Signals and questions |
| [Conversation Compiler](https://arxiv.org/abs/2603.29678) | Agent trace analysis | Views and evidence |
## 2. Trace the evidence
A **trace** records steps in a process. Keep each claim connected to its source.
- Read the research question.
- Locate the relevant figure or example.
- Keep source links with your notes.
- Record open questions for the next pass.
## 3. Keep code intact
```python
for paper in reading_list:
print(paper["title"], paper["url"])
```
Illustrative reading checklist. Open each source for the complete paper.
Translation Original structure preservedSimplified Chinese
for paper in reading_list:
print(paper["title"], paper["url"])
此处为阅读清单示例;完整内容请查阅各篇原文。
Aa
Your preferred termtrace →
Keep your terminology consistent with the domain and context.
Localized interface preview · Swipe to explore. Papers and scores use public metadata.
PAPER RADAR / MULTIDIMENSIONAL SCORING
Ranking evidence and preferences
Scores combine topic matching, source evidence for authors and institutions, publication age and your research interests. Inspect the contributing evidence when deciding what to read.
Reuse completed filtering. Browse cached papers without repeated source requests.
02
Search and loading status
See results arrive and follow each step.
03
Evidence and sources
Explore authors, research evidence and term origins as needed.
KNOWME / RESEARCH ATLAS
Research atlas and source papers
Public interactive atlas
Your research interests and accumulated reading shape author and institution weights within your private research system. Each paper’s personal score evolves with that evidence.
Opening the research map…
Enable local evolution to add evidence from Scholar author pages. Stored on your device; pause or clear at any time.
The map uses a prepared public sample. Counts describe this view; your own map changes with local evidence and interests.
Direction weighting, time decay and small-sample shrinkage keep personal signals contextual. Personal weights are calculated; coauthorship and visit counts do not directly measure paper quality.
YOUR RESEARCH. YOUR PERSPECTIVE.
The same paper. A different perspective.
Switch public papers and current example presets to inspect their scoring components.
Current example preset · Agents + reasoning, priority 1 each
Author terms and institutional G contributions for the selected preset
Evidence source
Fit / weight · G
Loading example results…
Author fit and weight are shown separately from institutional G; paper adjustments use the actual aggregate.
Base score—
+
Author adjustment—
+
Institution adjustment—
=
Personal score—
Keywords, sources and calculation
Author fit is a percentage; × is the author weight. Adjustments and totals come directly from the product result. Institution G values are not added together and do not determine whether the paper matches this preset. Base is evaluated per preset.
Current example presets. Public bibliography cached 2026-11-03; scores computed 2026-11-15. Base is evaluated separately for each preset.
Author, institution and paper names are used only to demonstrate the tool. They do not imply endorsement, affiliation or partnership. Bibliographic details link to their sources.
FROM THE GRAPH TO THE PAPER
From a connection to a paper.
Find an author, follow a shared paper and inspect personal weights and sources. Evidence stays within reach.
Install. Set up. Start reading. Find answers as you go.
1
Choose your toolDiscover papers with Radar. Read across languages with Translate.
2
Make it yoursChoose 1–3 topics in Radar. Save and test your model connection in Translate.
3
Keep readingBuild your saved papers and terminology for the next reading session.
How do I build my first paper cache?+
Choose your topics and run an online refresh. Then use cache-only mode to revisit the same date range and filters. Cache-only mode does not contact arXiv; refresh online for the latest papers.
How do I set up page annotations?+
Author profiles and Scholar search / arXiv details have separate controls. Compact mode keeps the KnowMe button and hides long status text and author coloring. Annotations use local records and a limited bundled index; a missing match does not imply a paper is unimportant.
How do I connect a translation model?+
In quick setup, choose a provider or compatible gateway, enter the model, endpoint and key, then save and test. Requests use that service’s allowance; matching text and settings can reuse the local cache.
How do text selection and shortcuts work?+
Enable the common features in quick setup and confirm the browser permissions. Defaults: ⌘⇧Y on Mac and Alt+Shift+Y on Windows. Change the keys and global scope in the browser’s extension shortcuts page. Refresh pages that were already open after an update.
Does my data sync automatically?+
Saved papers, cache, personal terms and history stay in the current browser and do not sync through your Google account. Export a backup before changing devices, browser profiles or uninstalling. Your chosen model service processes translations and connection tests.
Public store version checked on 2026-11-18: 1.2.6. The store controls extension availability; the CLI download is separate. Interface examples keep their recorded versions and scores.