This canonical paper page includes Commercialization Proof and Related Resources.
ARXIV:2603.18743 · AGENTS · SUBMITTED 20 MAR · 21:29 UTC · FRESHNESS STALE
ARXIV:2603.18743AGENTSSUBMITTED 20 MAR · 21:29 UTCFRESHNESS STALEHuichi Zhou · Siyuan Guo · Anjie Liu · Zhongwei Yu · Ziqin Gong · Bowen Zhao · +11 at arXiv
An agent that autonomously designs, adapts, and improves task-specific agents using a memory-based reinforcement learning framework and evolving externalized skills.
Opportunity summary
Pain An agent that autonomously designs, adapts, and improves task-specific agents using a memory-based reinforcement learning framework and evolving externalized skills.
Evidence 0 refs | 0 sources | 50% coverage
Blocker Evidence partial
An agent that autonomously designs, adapts, and improves task-specific agents using a memory-based reinforcement learning framework and evolving externalized skills. The system is built on a memory-based reinforcement learning framework with \emph{stateful prompts}, where…
We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing agent}: it autonomously constructs, adapts, and improves task-specific agents through experience. The system is built on a memory-based reinforcement learning…
ScienceToStartup currently rates this 8.0/10 on the public viability pass. We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing agent}: it autonomously constructs, adapts, and improves task-specific agents through…
Agents moved forward this cycle; last verified April 2026. Public score 8.0/10. Implementation evidence is present through a linked repository.
Continue into Read for claims, analysis, references, and neighboring papers.
mobile layout uses overflow-hidden min-w-0 break-wordsOpportunity summary
Score8.0Public score shown from the verified overall while the stale axis breakdown refreshesAnalysis summary
An agent that autonomously designs, adapts, and improves task-specific agents using a memory-based reinforcement learning framework and evolving externalized skills.
Loading BUILD…
Paper Pack
10.48550/arXiv.2603.18743An agent that autonomously designs, adapts, and improves task-specific agents using a memory-based reinforcement learning framework and evolving externalized skills.
Abstract
We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing agent}: it autonomously constructs, adapts, and improves task-specific agents through experience. The system is built on a memory-based reinforcement learning framework with \emph{stateful prompts}, where reusable skills (stored as structured markdown files) serve as persistent, evolving memory. These skills encode both behaviour and context, enabling the agent to carry forward knowledge across interactions. Starting from simple elementary skills (like Web search and terminal operations), the agent continually improves via the \emph{Read--Write Reflective Learning} mechanism introduced in \emph{Memento~2}~\cite{wang2025memento2}. In the \emph{read} phase, a behaviour-trainable skill router selects the most relevant skill conditioned on the current stateful prompt; in the \emph{write} phase, the agent updates and expands its skill library based on new experience. This closed-loop design enables \emph{continual learning without updating LLM parameters}, as all adaptation is realised through the evolution of externalised skills and prompts. Unlike prior approaches that rely on human-designed agents, Memento-Skills enables a generalist agent to \emph{design agents end-to-end} for new tasks. Through iterative skill generation and refinement, the system progressively improves its own capabilities. Experiments on the \emph{General AI Assistants} benchmark and \emph{Humanity's Last Exam} demonstrate sustained gains, achieving 26.2\% and 116.2\% relative improvements in overall accuracy, respectively. Code is available at https://github.com/Memento-Teams/Memento-Skills.
Source availability
PDF linkedThe paper record includes a public PDF URL.
Extraction status
Derived fallbackRead summaries are estimated from adjacent metadata, not verified extraction rows.
Proof status
partial0 refs; 0 sources; 50% coverage.
What was readable
Derived fallback: Estimated from adjacent evidence; not verified from source.
Viability
Time to MVP
Commercial
Export
Preparing verified analysis
Dimensions overall score 8.0
PROBLEM
An agent that autonomously designs, adapts, and improves task-specific agents using a memory-based reinforcement learning framework and evolving externalized skills. The system is built on a memory-based reinforcement learning framework with \emph{stateful prompts}, where reusab...
METHOD
We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing agent}: it autonomously constructs, adapts, and improves task-specific agents through experience. The system is built on a memory-based reinforceme...
RESULT
ScienceToStartup currently rates this 8.0/10 on the public viability pass. We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing agent}: it autonomously constructs, adapts, and improves task-specific a...
WHY NOW
Agents moved forward this cycle; last verified April 2026. Public score 8.0/10. Implementation evidence is present through a linked repository.
Experiments on the General AI Assistants benchmark and Humanity's Last Exam demonstrate sustained gains, achieving 26.2% and 116.2% relative improvements in overall accuracy, respectively.
Implication not extracted yet.
partial
Experiments on the General AI Assistants benchmark and Humanity's Last Exam demonstrate sustained gains, achieving 26.2% and 116.2% relative improvements in overall accuracy, respectively.
Implication not extracted yet.
partial
This closed-loop design enables continual learning without updating LLM parameters, as all adaptation is realised through the evolution of externalised skills and prompts.
Implication not extracted yet.
partial
In the read phase, a behaviour-trainable skill router selects the most relevant skill conditioned on the current stateful prompt; in the write phase, the agent updates and expands its skill library based on new experience.
Implication not extracted yet.
partial
Unlike prior approaches that rely on human-designed agents, Memento-Skills enables a generalist agent to design agents end-to-end for new tasks.
Implication not extracted yet.
partial
The approach may rely heavily on the initial quality of skill definitions and the ability to generalized beyond predefined skill sets.
Implication not extracted yet.
partial
These skills encode both behaviour and context, enabling the agent to carry forward knowledge across interactions.
Implication not extracted yet.
partial
Scalability and the interpretability of autonomous decisions might also pose challenges.
Implication not extracted yet.
partial
Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.
Concepts
Methods
Materials
Markets
Competitors
An agent that autonomously designs, adapts, and improves task-specific agents using a memory-based reinforcement learning framework and evolving externalized skills.
Segment
Agents
Adoption evidence
Public code linked for build inspection
Commercial read
8.0/10 public viability
Direct
Adjacent
Substitute
Unknown
No indexed public discussion is attached to 2603.18743 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.
Hacker News
Not indexed yet
Not indexed yet
Bluesky
Not indexed yet
Preview the source document here, or use the hero PDF action for a new tab.
Showing 20 of 21 references
CITED BY
No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.
Extension
Commercially relevant
Conflicting
Owned Distribution
Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.
1/3 checks · 33%
Build Passport
Build passport pending - Proof Lab budget No verified cost estimate / $7.00 cap
status
missing
reason
passport_row_missing
proof status
unverified
cost/budget
No verified cost estimate
confidence low
next verification path
Build brief missing until Build Passport data exists.
Source missing: Build Passport payload.
Experiment plan missing until prototype path is available.
No prototype path attached.
Validation checklist missing until required assets, cost, and regulatory flags are verified.
No checklist artifact is attached to the Build Passport payload.
Derived signals show verified:false until source-backed receipts exist.
Evidence coverage
OpportunityKernel evidence_receipt
0 refs / 0 sources / 50% coverage
stale
Verify missing sources before using this as buyer proof. verified:false
Build readiness
BuildPassport EvidenceState
passport absent
stale
Run Proof Lab or inspect typed missing state. verified:false
Artifact maturity
GitHub and Hugging Face maturity payloads
No public artifact surface observed
stale
Open source artifacts or mark the gap as missing. verified:false
Technical feasibility
partial
Current read
Runnable path is not fully verified.
Evidence
No Build Passport payload attached.
Gaps
Next test
Run minimal reproduction from the Build Passport prototype path.
Market urgency
missing
Current read
Buyer urgency is not verified from source.
Evidence
0 references, 0 sources, 50% evidence coverage.
Gaps
Next test
Collect buyer interview, deployment evidence, or cited demand signal.
Buyer clarity
missing
Current read
No budget owner is verified for this paper.
Evidence
Build tab has no CRM, procurement, or operator source.
Gaps
Next test
Map target operator, economic buyer, and procurement trigger.
Defensibility
missing
Current read
Defensibility signals are missing.
Evidence
No defensibility receipt attached.
Gaps
Next test
Refresh defensibility bars with source receipts.
Integration burden
missing
Current read
No public implementation surface observed.
Evidence
No GitHub or Hugging Face payload attached.
Gaps
Next test
Write integration checklist from prototype path and target workflow.
Capital intensity
missing
Current read
No observed cost estimate is verified.
Evidence
Cost passport has no observed_usd value.
Gaps
Next test
Run cost passport or mark the cost field not applicable.
Regulatory load
missing
Current read
No regulatory classification is attached.
Evidence
Build Passport ledger does not include regulatory flags.
Gaps
Next test
Classify regulatory flags before commercialization planning.
No named scientific founder assigned.
Paper authors are not treated as operators without consent.
People
No named person assigned.
Gaps
Next verification path
Prototype owner missing.
Build Passport does not name an implementer.
People
No named person assigned.
Gaps
Next verification path
Operator workflow not sourced.
No buyer or workflow interview attached.
People
No named person assigned.
Gaps
Next verification path
No GTM owner verified.
No CRM or outreach source attached.
People
No named person assigned.
Gaps
Next verification path
Regulatory need unclassified.
No clinical or regulatory source attached.
People
No named person assigned.
Gaps
Next verification path
ARTIFACTS
No public artifacts yet.
DEFENSIBILITY
Defensibility and confidence evidence pending.
WATCHTOWER
No verified watchtower monitor rows yet.
FORESIGHT
No prediction yet — minted on next Foresight batch.
OPPORTUNITYKERNEL CHANGES SINCE LAST VIEW
No verified OpportunityKernel changes since the last view.
COMPETITIVE LANDSCAPE UPDATES
No verified competitive landscape changes yet.
RELATED PAPER UPDATES
No verified related paper changes yet.
SIGNAL CANVAS HISTORY AND DELTAS
No Signal Canvas history deltas yet.
TIMELINE
Save this paper to start tracking momentum - commits, demos, and score changes appear here.
No tracked events yet.
Score trend will appear after multiple data points.
BUZZ
Buzz trend pending.