Arch-Router: Aligning LLM Routing with Human Preferences · HackerPapers discussions

Arch-Router: Aligning LLM Routing with Human Preferences — mentioned by honorable_coder

Mon, 22 Sep 2025 18:03:21 GMT

Today we’re shipping a major update to ArchGW (an edge and service proxy for agents [1]): a unified router that supports three strategies for directing traffic to LLMs — from explicit model names, to semantic aliases, to dynamic preference-aligned routing. Here’s how each works on its own, and how they come together. Preference-aligned routing decouples task detection (e.g., code generation, image editing, Q&A) from LLM assignment. This approach captures the preferences developers establish when testing and evaluating LLMs on their domain-specific workflows and tasks. So, rather than relying…

Paper and discussion history. A mention is not an endorsement.

Arch-Router: Aligning LLM Routing with Human Preferences — HN submission

Sun, 21 Sep 2025 17:45:54 GMT

Show HN: Model-literals, model-aliases, and preference-aligned routing for LLMs

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Arch-Router: Aligning LLM Routing with Human Preferences — HN submission

Sat, 09 Aug 2025 09:21:40 GMT

Arch-Router: Aligning LLM Routing with Human Preferences

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Arch-Router: Aligning LLM Routing with Human Preferences — HN submission

Sun, 03 Aug 2025 06:32:04 GMT

Show HN: Arch-Router – Aligning LLM Routing with Human Preferences

Hi HN — we're the team behind ArchGW [1], an edge and service proxy for agents written in Rust, and we just recently published our research on LLM Routing: https://arxiv.org/abs/2506.16655 As teams integrate multiple LLMs - each with different strengths, styles, or cost/latency profiles — routing the right prompt to the right model becomes a critical part of the application design. But it's still an open problem. Most routing systems fall into two camps: - Embedding-based routers use intent classifiers — label a prompt as “support,” “SQL,” or “math,” then route to a matching model. This works…

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Arch-Router: Aligning LLM Routing with Human Preferences — HN submission

Sat, 02 Aug 2025 21:42:16 GMT

Arch-Router: Aligning LLM Routing with Human Preferences

9 points; 2 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Arch-Router: Aligning LLM Routing with Human Preferences — HN submission

Tue, 22 Jul 2025 17:52:01 GMT

Show HN: RouteGPT – model routing on ChatGPT aligned to user preferences

Hey HN I had a personal itch to scratch, and thought that it might be useful to others: If you are a ChatGPT pro user like me, you are probably tired of pedaling to the model selector drop down to pick a model, prompt that model and then repeat that cycle all over again. So I built RouteGPT to end that pedaling. RouteGPT is a Chrome extension for chatgpt.com that automatically selects the right OpenAI model for your prompt based on preferences you define. For example: “creative novel writing, story ideas, imaginative prose” → GPT-4o, or “critical analysis, deep insights, and market research ”…

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Arch-Router: Aligning LLM Routing with Human Preferences — mentioned by honorable_coder

Fri, 18 Jul 2025 04:50:41 GMT

Hi HN — we're the team behind Arch (an open-source edge and service proxy for agents)[1], and today we're releasing Arch-Router (https://huggingface.co/katanemo/Arch-Router-1.5B), a 1.5B LLM router model designed to align to user-defined preferences, not public benchmarks and leader boards. As teams integrate multiple LLMs - each with different strengths, styles, or cost/latency profiles — routing the right prompt to the right model becomes a critical part of the application design. But it's still an open problem. Most routing systems fall into two camps: - Embedding-based routers use intent…

Paper and discussion history. A mention is not an endorsement.

Arch-Router: Aligning LLM Routing with Human Preferences — HN submission

Thu, 17 Jul 2025 20:29:12 GMT

Show HN: 1.5B LLM routing model that aligns to preferences, not leaderboards

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Arch-Router: Aligning LLM Routing with Human Preferences — mentioned by honorable_coder

Tue, 15 Jul 2025 17:24:05 GMT

Model: https://huggingface.co/katanemo/Arch-Router-1.5B Paper: https://arxiv.org/abs/2506.16655 Integrated experience via Arch: https://github.com/katanemo/archgw

Paper and discussion history. A mention is not an endorsement.

Arch-Router: Aligning LLM Routing with Human Preferences — mentioned by honorable_coder

Mon, 14 Jul 2025 22:40:21 GMT

Is model choice a core design consideration. Or will Kiro not let developers chose the underlying model? What if I want to set preferences for the underlying LLM for different usage scenarios? For example, for a quick and snappy understanding of a single file id want to use a fast model that doesn't cost me an arm and a leg. Recent research on preference-aligned LLM routing here: https://arxiv.org/abs/2506.16655

Paper and discussion history. A mention is not an endorsement.

Arch-Router: Aligning LLM Routing with Human Preferences — HN submission

Tue, 01 Jul 2025 17:13:11 GMT

Show HN: Arch-Router – 1.5B model for LLM routing by preferences, not benchmarks

Hi HN — we're the team behind Arch (https://github.com/katanemo/archgw), an open-source proxy for LLMs written in Rust. Today we're releasing Arch-Router (https://huggingface.co/katanemo/Arch-Router-1.5B), a 1.5B router model for preference-based routing, now integrated into the proxy. As teams integrate multiple LLMs - each with different strengths, styles, or cost/latency profiles — routing the right prompt to the right model becomes a critical part of the application design. But it's still an open problem. Most routing systems fall into two camps: - Embedding-based routers use intent…

66 points; 15 discussion replies on HN. Paper and source history. A submission is not an endorsement.