This canonical paper page includes Commercialization Proof and Related Resources.
ARXIV:2603.28052 · LLM HARNESS OPTIMIZATION · SUBMITTED 31 MAR · 20:20 UTC · FRESHNESS STALE
ARXIV:2603.28052LLM HARNESS OPTIMIZATIONSUBMITTED 31 MAR · 20:20 UTCFRESHNESS STALEYoonho Lee · Roshen Nair · Qizheng Zhang · Kangwook Lee · Omar Khattab · Chelsea Finn · arXiv
Automate the creation of LLM harnesses to significantly improve performance and reduce context token usage.
Opportunity summary
Pain Automate the creation of LLM harnesses to significantly improve performance and reduce context token usage.
Evidence 76 refs | 4 sources | 50% coverage
Blocker Evidence unverified
Automate the creation of LLM harnesses to significantly improve performance and reduce context token usage. Yet harnesses are still designed largely by hand, and existing text optimizers are poorly matched to this setting because…
The performance of large language model (LLM) systems depends not only on model weights, but also on their harness: the code that determines what information to store, retrieve, and present to the model. Yet…
ScienceToStartup currently rates this 7.0/10 on the public viability pass. On online text classification, Meta-Harness improves over a state-of-the-art context management system by 7.7 points while using 4x fewer context tokens.
LLM Harness Optimization moved forward this cycle; last verified April 2026. Public score 7.0/10.
Continue into Read for claims, analysis, references, and neighboring papers.
mobile layout uses overflow-hidden min-w-0 break-wordsOpportunity summary
Score7.0Public score shown from the verified overall while the stale axis breakdown refreshesAnalysis summary
Automate the creation of LLM harnesses to significantly improve performance and reduce context token usage.
Loading BUILD…
Paper Pack
10.48550/arXiv.2603.28052Automate the creation of LLM harnesses to significantly improve performance and reduce context token usage.
Abstract
The performance of large language model (LLM) systems depends not only on model weights, but also on their harness: the code that determines what information to store, retrieve, and present to the model. Yet harnesses are still designed largely by hand, and existing text optimizers are poorly matched to this setting because they compress feedback too aggressively. We introduce Meta-Harness, an outer-loop system that searches over harness code for LLM applications. It uses an agentic proposer that accesses the source code, scores, and execution traces of all prior candidates through a filesystem. On online text classification, Meta-Harness improves over a state-of-the-art context management system by 7.7 points while using 4x fewer context tokens. On retrieval-augmented math reasoning, a single discovered harness improves accuracy on 200 IMO-level problems by 4.7 points on average across five held-out models. On agentic coding, discovered harnesses surpass the best hand-engineered baselines on TerminalBench-2. Together, these results show that richer access to prior experience can enable automated harness engineering.
Source availability
PDF linkedThe paper record includes a public PDF URL.
Extraction status
Parse run linkedA document parse run is attached to this paper.
Proof status
unverified76 refs; 4 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 7.0
PROBLEM
Automate the creation of LLM harnesses to significantly improve performance and reduce context token usage. Yet harnesses are still designed largely by hand, and existing text optimizers are poorly matched to this setting because they compress feedback too aggressively.
METHOD
The performance of large language model (LLM) systems depends not only on model weights, but also on their harness: the code that determines what information to store, retrieve, and present to the model. Yet harnesses are still designed largely by hand, and existing text optimiz...
RESULT
ScienceToStartup currently rates this 7.0/10 on the public viability pass. On online text classification, Meta-Harness improves over a state-of-the-art context management system by 7.7 points while using 4x fewer context tokens.
WHY NOW
LLM Harness Optimization moved forward this cycle; last verified April 2026. Public score 7.0/10.
Meta-Harness improves online text classification accuracy while using a smaller input context.
Directly stated in abstract and analysis with specific numeric comparisons in Table 2 and text.
partial
Meta-Harness improves accuracy on 200 IMO-level problems by 4.7 points on average across five held-out models.
Explicitly stated in abstract and supported by Table 6 showing average improvement.
partial
On agentic coding, discovered harnesses surpass the best hand-engineered baselines on TerminalBench-2.
Directly stated in abstract and supported by Figure 1 showing performance comparison.
partial
This paper considers settings that yield orders-of-magnitude more context per artifact evaluation.
Supported by Table 1 showing Meta-Harness with 10.0 Mtok/iter versus much lower values for other methods, with explanatory text.
partial
Access to raw execution traces is the key ingredient for enabling harness search.
Directly stated in analysis section interpreting ablation results.
partial
Given only the current metrics and the desired trade-off, the proposer is able to discover harnesses across a broad range of the frontier.
Stated in analysis with reference to Pareto frontier and optimization capability.
partial
Meta-Harness outperforms the next best method by 2.9 points on these 9 previously unseen tasks.
Directly supported by Table 5 showing test accuracy comparisons.
partial
Changing the harness around a fixed large language model (LLM) can produce a 6 × performance gap on the same benchmark.
Explicitly stated in introduction with citation, establishing the importance of harness optimization.
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
Automate the creation of LLM harnesses to significantly improve performance and reduce context token usage.
Segment
LLM Harness Optimization
Adoption evidence
No public code link in the paper record yet
Commercial read
7.0/10 public viability
Direct
Adjacent
Substitute
Unknown
No indexed public discussion is attached to 2603.28052 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.
Reference metadata is not materialized in the public index yet. The source PDF remains the authority; cache refresh is optional.
CITED BY
No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.
Foundation
Extension
Commercially relevant
Conflicting
Owned Distribution
Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.
3/3 checks · 100%
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
76 refs / 4 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
partial
Current read
Research evidence exists; buyer urgency still needs source proof.
Evidence
76 references, 4 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.