update docs: add paper, replace tau-bench charts with updated bar charts

[sanchit056]

Adds the fastWorkflow paper PDF to the paper/ directory and links it at the top of the README. Replaces the old tau-bench bar chart with updated PNG versions for both Retail and Airline benchmarks.

Summary by Sourcery

Add a link to the fastWorkflow paper in the README and update benchmark charts to use the latest TauBench performance images.

Documentation:

• Link the fastWorkflow paper PDF from the README for easier access to the publication.
• Refresh TauBench Retail and Airline benchmark charts in the README with updated PNG bar chart images.

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

Adds a link to the new fastWorkflow paper in the README and updates the TauBench benchmark images to use new PNG bar charts for Retail and Airline performance results.

File-Level Changes

Change	Details	Files
Expose the fastWorkflow paper directly from the README.	Insert a prominent link at the top of the README pointing to the fastWorkflow paper PDF under the paper/ directory Use descriptive link text summarizing the paper title to improve discoverability	README.md
Refresh TauBench benchmark visuals to use updated PNG bar charts.	Replace the previous TauBench Retail image reference with a new PNG chart filename and clearer alt text Replace the previous TauBench Airline image reference with a new PNG chart filename and clearer alt text while keeping table layout and styling intact	README.md

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey - I've left some high level feedback:

• Linking directly to paper/fastWorkflow_Closing_the_Performance_Gap_Between_Small_and_Frontier_Language_Models_for_Conversational_Agents.pdf assumes the file will be available at that relative path in all distribution contexts (e.g., rendered docs site, PyPI README); consider confirming or using an absolute or repository-root-relative URL to avoid broken links.
• The alt text for the TauBench images now differs slightly from the previous naming (Tau Bench vs TauBench and omission of fastWorkflow), so consider aligning the wording to maintain consistency with the surrounding text and any references in the paper.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- Linking directly to `paper/fastWorkflow_Closing_the_Performance_Gap_Between_Small_and_Frontier_Language_Models_for_Conversational_Agents.pdf` assumes the file will be available at that relative path in all distribution contexts (e.g., rendered docs site, PyPI README); consider confirming or using an absolute or repository-root-relative URL to avoid broken links.
- The alt text for the TauBench images now differs slightly from the previous naming (`Tau Bench` vs `TauBench` and omission of `fastWorkflow`), so consider aligning the wording to maintain consistency with the surrounding text and any references in the paper.

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}