Bridging Large-Model Reasoning and Real-Time Control via Agentic Fast-Slow Planning

Bridging Large-Model Reasoning and Real-Time Control via Agentic Fast-Slow Planning | Signal Canvas | ScienceToStartup

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/bridging-large-model-reasoning-and-real-time-control-via-agentic-fast-slow-planning

stale

Proof freshness: stale
Proof status: partial
Display score: 7/10
Last proof check: 2026-04-03
Score updated: 2026-04-03
Score fresh until: 2026-05-03
References: 0
Source count: 0
Coverage: 67%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

Agent Handoff

Canonical ID bridging-large-model-reasoning-and-real-time-control-via-agentic-fast-slow-planning | Route /signal-canvas/bridging-large-model-reasoning-and-real-time-control-via-agentic-fast-slow-planning

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/bridging-large-model-reasoning-and-real-time-control-via-agentic-fast-slow-planning

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "bridging-large-model-reasoning-and-real-time-control-via-agentic-fast-slow-planning",
    "query_text": "Summarize Bridging Large-Model Reasoning and Real-Time Control via Agentic Fast-Slow Planning"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "Bridging Large-Model Reasoning and Real-Time Control via Agentic Fast-Slow Planning",
  "normalized_query": "2604.01681",
  "route": "/signal-canvas/bridging-large-model-reasoning-and-real-time-control-via-agentic-fast-slow-planning",
  "paper_ref": "bridging-large-model-reasoning-and-real-time-control-via-agentic-fast-slow-planning",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Evidence Receipt

Route status: building

Claims: 8

References: Pending verification

Proof: Verification pending

Freshness state: computing

Source paper: Bridging Large-Model Reasoning and Real-Time Control via Agentic Fast-Slow Planning

PDF: https://arxiv.org/pdf/2604.01681v1

Repository: https://github.com/cjychenjiayi/icra2026_AFSP

Source count: Pending verification

Coverage: 67%

Last proof check: 2026-04-03T20:30:33.289Z

Signal Canvas receipt window

Ready for execution: Bridging Large-Model Reasoning and Real-Time Control via Agentic Fast-Slow Planning

/buildability/bridging-large-model-reasoning-and-real-time-control-via-agentic-fast-slow-planning

Build Nowready

Subject: Bridging Large-Model Reasoning and Real-Time Control via Agentic Fast-Slow Planning

Verdict

Preparing verified analysis

GitHub Code Pulse

Stars

Health

Last commit

3/5/2026

Forks

Open repository

Claim map

Strong 8Mixed 0Weak 0

Evidencepartial
reducing lateral deviation by up to 45% and completion time by over 12% compared to pure MPC and an A*-guided MPC baseline.
Implicationpartial
Directly stated in abstract with specific numeric improvement
Verificationpartial
partial
Evidencepartial
reducing lateral deviation by up to 45% and completion time by over 12% compared to pure MPC and an A*-guided MPC baseline.
Implicationpartial
Directly stated in abstract with specific numeric improvement
Verificationpartial
partial
Evidencepartial
Perception2Decision compresses scenes into ego-centric topologies using an on-vehicle Vision-Language Model (VLM) detector, then maps them to symbolic driving directives in the cloud with an LLM decision maker - reducing bandwidth and delay while preserving interpretability.
Implicationpartial
Directly described in abstract as a core component of the method
Verificationpartial
partial
Evidencepartial
Semantic-Guided A* embeds language-derived soft costs into classical search to bias solutions toward feasible trajectories
Implicationpartial
Directly described in abstract as a technical component of the method
Verificationpartial
partial
Evidencepartial
Existing approaches either (i) let Large Language Models (LLMs) generate trajectories directly - brittle, hard to verify, and latency-prone
Implicationpartial
Directly stated in abstract as limitation of existing approaches
Verificationpartial
partial
Evidencepartial
or (ii) adjust Model Predictive Control (MPC) objectives online - mixing slow deliberation with fast control and blurring interfaces.
Implicationpartial
Directly stated in abstract as limitation of existing approaches
Verificationpartial
partial
Evidencepartial
while an Agentic Refinement Module adapts planner hyperparameters using feedback and memory.
Implicationpartial
Directly described in abstract as a technical component of the method
Verificationpartial
partial
Evidencepartial
a hierarchical framework that decouples perception, reasoning, planning, and control across natural timescales.
Implicationpartial
Directly stated in abstract as a core design principle
Verificationpartial
partial

Author intelligence and commercialization panels stay hidden until the proof receipt is verified, cites at least 3 references, includes at least 2 sources, and clears 50% coverage. The paper narrative and citation surfaces remain public while verification is pending.

Bridging Large-Model Reasoning and Real-Time Control via Agentic Fast-Slow Planning

Use Signal Canvas as the narrative proof surface

Use this Signal Canvas via API or MCP

Signal Canvas proof surface