AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents

AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents | Signal Canvas | ScienceToStartup

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/androtmem-from-interaction-trajectories-to-anchored-memory-in-long-horizon-gui-agents

stale

Proof freshness: stale
Proof status: unverified
Display score: 8/10
Last proof check: 2026-03-20
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 50%

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 androtmem-from-interaction-trajectories-to-anchored-memory-in-long-horizon-gui-agents | Route /signal-canvas/androtmem-from-interaction-trajectories-to-anchored-memory-in-long-horizon-gui-agents

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/androtmem-from-interaction-trajectories-to-anchored-memory-in-long-horizon-gui-agents

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "androtmem-from-interaction-trajectories-to-anchored-memory-in-long-horizon-gui-agents",
    "query_text": "Summarize AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents",
  "normalized_query": "2603.18429",
  "route": "/signal-canvas/androtmem-from-interaction-trajectories-to-anchored-memory-in-long-horizon-gui-agents",
  "paper_ref": "androtmem-from-interaction-trajectories-to-anchored-memory-in-long-horizon-gui-agents",
  "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: AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents

PDF: https://arxiv.org/pdf/2603.18429v1

Repository: https://github.com/CVC2233/AndroTMem

Source count: Pending verification

Coverage: 50%

Last proof check: 2026-03-20T21:29:19.526Z

Signal Canvas receipt window

Ready for execution: AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents

/buildability/androtmem-from-interaction-trajectories-to-anchored-memory-in-long-horizon-gui-agents

Build Nowready

Subject: AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents

Verdict

Build Now

Preparing verified analysis

GitHub Code Pulse

Cached

Stars

Health

Last commit

3/23/2026

Forks

Open repository

Claim map

Strong 8Mixed 0Weak 0

Evidencepartial
comprises 1,069 tasks with 34,473 interaction steps (avg. 32.1 per task, max. 65)
Implicationmissing
Implication not extracted yet.
Verificationpartial
partial
Evidencepartial
as interaction sequences grow longer, performance drops are driven mainly by within-task memory failures, not isolated perception errors or local action mistakes
Implicationmissing
Implication not extracted yet.
Verificationpartial
partial
Evidencepartial
ASM consistently outperforms full-sequence replay and summary-based baselines, improving TCR by 5%-30.16% and AMS by 4.93%-24.66%
Implicationmissing
Implication not extracted yet.
Verificationpartial
partial
Evidencepartial
improving TCR by 5%-30.16% and AMS by 4.93%-24.66%
Implicationmissing
Implication not extracted yet.
Verificationpartial
partial
Evidencepartial
AndroTMem-Bench is designed to enforce strong step-to-step causal dependencies, making sparse yet essential intermediate states decisive for downstream actions
Implicationmissing
Implication not extracted yet.
Verificationpartial
partial
Evidencepartial
represents interaction sequences as a compact set of causally linked intermediate-state anchors to enable subgoal-targeted retrieval and attribution-aware decision making
Implicationmissing
Implication not extracted yet.
Verificationpartial
partial
Evidencepartial
Replaying full interaction sequences is redundant and amplifies noise, while summaries often erase dependency-critical information and traceability
Implicationmissing
Implication not extracted yet.
Verificationpartial
partial
Evidencepartial
effective interaction memory under prevailing paradigms remains under-explored
Implicationmissing
Implication not extracted yet.
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.

AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents

Use Signal Canvas as the narrative proof surface

Use this Signal Canvas via API or MCP

Signal Canvas proof surface