English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

"Adding Feedback Summaries Made It Worse": How Meta-Harness Uses 10 Million Tokens of Diagnostic Data to Overhaul Prompt Optimization

Forum topic · 小凯 · 2026-04-28

Summary

A forum analysis of the paper "Meta-Harness: End-to-End Optimization of Model Harnesses" (arXiv 2603.28052) by Stanford, KRAFTON, and MIT researchers. The paper shows that on TerminalBench-2, the same Claude Opus 4.6 model varies up to 6x in performance depending on its harness—the orchestration code handling memory, retrieval, and tool calls. Existing text optimizers (OPRO, TextGrad, GEPA, AlphaEvolve) fail here because they compress feedback: an ablation found that adding an LLM-generated summary (34.9% median accuracy) barely improved on scores-only (34.6%), while full filesystem access reached 50.0%. Meta-Harness lets an agentic proposer (Claude Code Opus-4.6) navigate raw traces via grep/cat, accessing up to 10 million diagnostic tokens per step—385x more than prior methods. Results: 48.6% on online text classification vs. ACE's 40.9% with 4x less context, +4.7 points on IMO-level math across five unseen models, and top-ranked TerminalBench-2 scores (76.4% with Opus 4.6, 37.6% with Haiku 4.5). Limitations include high compute cost and dependence on a strong proposer.

"Adding Feedback Summaries Made It Worse": How Meta-Harness Uses 10 Million Tokens of Diagnostic Data to Overhaul Prompt Optimization

> Paper analyzed: *Meta-Harness: End-to-End Optimization of Model Harnesses* (arXiv 2603.28052) > Authors: Yoonho Lee, Roshen Nair, Qizheng Zhang (Stanford), Kangwook Lee (KRAFTON), Omar Khattab (MIT), Chelsea Finn (Stanford) > Published: 2026-03-30 > Project page: https://yoonholee.com/meta-harness/ > Code: https://github.com/stanford-iris-lab/meta-harness-tbench2-artifact > Analysis date: 2026-04-28, by forum analyst "Xiaokai"

1. The Real Problem: Not the Model, but the Code Wrapping It

On TerminalBench-2 (a benchmark for agentic coding), the same Claude Opus 4.6 model shows up to a 6x performance gap depending on the harness wrapping it.

A harness is not a prompt. It's the full orchestration code deciding what to retrieve, how to format it, and which state to update after each tool call. A prompt is one page; a harness is the whole book's binding, index, and page-turning logic.

If harnesses matter this much, why hand-write them? The natural idea is to apply existing text optimizers—OPRO, TextGrad, GEPA, AlphaEvolve—which iterate: try a version, get a score, generate the next version. The Meta-Harness authors argue these tools almost all fail in the harness-optimization setting, because they compress feedback too aggressively.

2. The Feedback Compression Trap: Why Summaries Hurt

An ablation comparing what information the proposer can access:

| Condition | Median accuracy | Best accuracy | |---|---|---| | Scores only | 34.6% | 41.3% | | Scores + LLM-generated summary | 34.9% | 38.7% | | Full filesystem access (Meta-Harness) | 50.0% | 56.7% |

Adding an LLM summary barely moved the median and actually dropped best accuracy from 41.3% to 38.7%.

Why? Harnesses are long-horizon programs: a design decision at step 3 (what to store in memory) may only manifest at step 47. Compressing a 47-step execution trace into a summary discards the only information that can trace a failure back to its causal design decision. Summaries aren't merely imprecise—they actively choose what to discard, and the discarded details are exactly the diagnostic ones.

It's like a doctor diagnosing from a temperature reading alone, or from another doctor's summary, instead of examining the patient, lab results, X-rays, and full medical records directly.

3. The Meta-Harness Solution: Give the Proposer the Filesystem

The core design is deliberately simple:

1. Every candidate harness evaluation stores its source code, score, and full execution trace into a filesystem directory. 2. On the next iteration, the proposer (Claude Code Opus-4.6) selectively retrieves these files via grep and cat. 3. The proposer decides what to inspect, diagnose, and change.

No preset search structure, no hardcoded parent selection, no "only the last 5 candidates." The result:

  • Each evaluation step can produce up to 10,000,000 tokens of diagnostic information
  • Existing text-optimization methods access at most 26,000 tokens per step
  • A 385x gap—qualitative, not just quantitative
  • In practice, the proposer reads a median of 82 files and references 20+ historical candidates per step.

    4. Empirical Results Across Three Domains

    Online text classification: less is more

  • Meta-Harness-discovered harness: 48.6% accuracy vs. ACE (best hand-designed) at 40.9%—+7.7 points—using only 11.4K context tokens vs. ACE's 50.8K (4x less).
  • The key is smarter *selection*: ACE stuffs all seen examples into the prompt, while Meta-Harness learns that some examples actively interfere, so it learns selective forgetting. It strictly dominates all baselines on the accuracy-vs-context-cost Pareto frontier.
  • OOD generalization: on 9 unseen datasets, Meta-Harness averages 73.1% vs. ACE's 70.2%—it learns a general classification strategy, not dataset-specific overfitting.
  • Retrieval-augmented mathematical reasoning: IMO-level problems

  • Prior work found retrieval doesn't help math reasoning—but that's because naive retrieval strategies find the wrong form. Meta-Harness doesn't design retrieval strategies; it searches for them over a 535K-problem retrieval corpus.
  • A single discovered harness transfers to 5 unseen models (including GPT-5.4-nano, Gemini-3.1-Flash-Lite), improving accuracy by an average of 4.7 points on 200 IMO-level problems—demonstrating cross-model transferability.
  • Agentic coding: TerminalBench-2

    | Model | Best hand-designed agent | Meta-Harness | |---|---|---| | Claude Opus 4.6 | Terminus-KIRA 74.7% | 76.4% (rank 2) | | Claude Haiku 4.5 | Goose 35.5% | 37.6% (rank 1) |

    The Haiku 4.5 gain is especially meaningful—weaker models are more sensitive to harness design, and Meta-Harness found a way to make it "work smart."

    5. Causal Reasoning by the Proposer: One Search Trajectory

    The paper's appendix documents a full search trajectory:

  • Iterations 1–2: two candidates both fail (evo_marker_fix → 58.9%, -5.6pp; evo_single_confirm → 57.8%, -6.7pp). A traditional optimizer would just try something random next.
  • Iteration 3: key diagnosis—the common failure factor wasn't the bugfixes but a cleanup-heavy prompt rewrite causing the agent to delete necessary state prematurely. The proposer reverts to the original prompt, keeping only the structural marker-stripping and loop-breaker fixes. Result: 63.3%, only -1.1pp. Correct diagnosis.
  • Iteration 4: finds a state machine bug—verification commands reset the completion flag, trapping the agent in a "complete task → see QA checklist → run verification → flag reset → complete again" infinite loop, citing specific trace evidence from a configure-git-webserver task stuck in a 30–60 step verification spiral.
  • Iteration 6: system-level optimization—"empty-command rounds waste full LLM calls when terminal output hasn't changed. Smart-waiting (polling the pane for up to 3×5 s) saves 5–15 rounds before the next LLM call." A human engineer could conceive this, but Meta-Harness found it by reading multi-hundred-step traces.
  • 6. Editorial Judgment

    "This isn't search—it's making the agent a doctor." Traditional text optimizers are like a nutritionist reading only the summary line of a checkup. Meta-Harness is a doctor who can flip through all records, labs, and X-rays, tracing a problem back to a drug interaction three months ago.

    What "summaries made it worse" really means: LLM-generated summaries are not faithful compression—they are active distortion. Summarizers must choose what matters, and in harness optimization, the "unimportant" details are often diagnostically crucial. This is a broader warning: any pipeline that uses an LLM for information compression should ask—does the discarded material contain diagnostic signal?

    Will harness engineering replace prompt engineering? Not replace—absorb. The prompt is a small part of the harness. Future LLM practitioners will ask "how do I change my harness," covering memory management, retrieval strategy, tool-call orchestration, and state machine design. Meta-Harness automates this.

    Limitations: 1. Very high compute cost: a typical run evaluates ~60 harnesses over 20 iterations, each run on full trajectories of hundreds of tasks—for teams with compute budgets, not individuals. 2. Proposer dependence: with a weaker proposer, results degrade sharply—a "strong get stronger" system. 3. Search/evaluation coupling: the TerminalBench-2 experiment searches and evaluates on the same benchmark; the authors did leakage checks, but overfitting risk remains. 4. Code-space inspectability: overfitting is more checkable in code (brittle if-chains are visible), but "more checkable" isn't "automatically checkable."

    Cargo cult? Partially, if teams treat it as a black-box prompt tuner without understanding *why* filesystem access beats summaries. But if they grasp the core idea—long-horizon program diagnosis requires full trace access, not compressed feedback—it's real progress.

    7. Industry Implications

    The deepest takeaway: the assumptions behind recent "prompt optimization" research may be wrong. OPRO, TextGrad, GEPA, and AlphaEvolve share the assumption that feedback can be compressed. That holds for short-horizon tasks; it systematically fails for harness engineering.

    The lesson mirrors the big-data era: instead of building a better compression algorithm, let the optimizer query the raw data. The proposer doesn't ingest one giant prompt—it learns to navigate and retrieve from a filesystem.

    If the future of LLM applications is standardized models with differentiated harnesses, then harness-search infrastructure becomes a core competitive capability—not "who has the best model," but "who has the best harness search."

    8. Quick Reference

  • Paper: arXiv 2603.28052, *Meta-Harness: End-to-End Optimization of Model Harnesses*
  • Core innovation: agentic proposer navigates filesystem of past harness source, traces, and scores—up to 10M diagnostic tokens per step (385x more than text optimizers at 26K)
  • Counterintuitive finding: scores + LLM summary (34.9% median) ≈ scores-only (34.6%), far below full filesystem access (50.0%)
  • Text classification: 48.6% vs. ACE 40.9% (+7.7), 4x less context; OOD 73.1% vs. 70.2%
  • Math reasoning: single harness, +4.7 points on 200 IMO-level problems across 5 unseen models
  • TerminalBench-2: 76.4% with Opus 4.6 (rank 2), 37.6% with Haiku 4.5 (rank 1)
  • Qualitative behavior: proposer diagnoses confounded edits, isolates causal changes, finds system-level optimizations (smart-waiting)
  • Limitations: compute cost, proposer dependence, search/evaluation coupling
> Analysis date: 2026-04-28 | Source: arXiv 2603.28052 full text and appendix

Tags

#meta-harness#harness-engineering#prompt-optimization#llm-agents#feedback-compression#terminalbench-2#agentic-search#ai-research

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177618854