An agent harness can improve by turning observed failures into small, testable changes to prompts, tools, context management, control flow, memory, and orchestration. To tell whether those changes generalize rather than memorize a benchmark, keep optimization tasks and scores away from the final evaluator, screen edits for benchmark-specific logic, and compare against simple search baselines using matched budgets. Recent studies report encouraging results in some settings, but other work finds limited transfer and no consistent advantage over test-time scaling; no single score establishes a universal effect.
What changes when you improve an agent harness?
A harness is the software around a language-model agent: it shapes what information the model sees, which tools it can call, how context is managed, and how execution and completion are controlled. Harness improvement changes that surrounding system rather than necessarily changing the underlying model. Several recent studies hold the model fixed while evolving or optimizing the harness, making the harness the focus of the comparison.
That distinction matters because an improved task score could come from a better harness, a different model, more inference compute, or exposure to the evaluation cases. A credible comparison records what changed and keeps those possible explanations separate.
What recent results show—and what they do not
The reported outcomes below come from different models, benchmarks, splits, and evaluation procedures. They are useful examples of what authors have observed in their own setups, not directly comparable estimates of which method is best.
The Tool Desk
Outbyte PC Repair FREERepair Windows errors before they cause bigger problemsFix Now →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →#1 Best Overall
- Read Before You Buy — No Video Output: These adapters support charging and USB 2.0 data transfer, but cannot transmit video signals. Except for standard USB webcams (which use USB data only), they are not compatible with HDMI/DisplayPort cables, video-capable USB-C hubs, or docking stations with video output.
- Convert USB-A Ports to USB-C: Designed to connect USB-C earphones, cables, flash drives, card readers, and other USB-C accessories to standard USB-A ports. Plug-and-play with no drivers or software required.
- Aluminum Alloy Housing: Built with a sturdy aluminum alloy shell that aids in heat dissipation and protects against daily wear and scratches. Designed to maintain a stable and secure connection.
- Compact & Travel-Friendly: The ultra-compact design allows the adapter to stay plugged into your device without blocking adjacent ports or adding bulk, reducing wear and tear on your original USB ports.
- 12-Month Warranty: Backed by a 12-month manufacturer warranty for peace of mind. Designed to meet strict quality control standards for reliable everyday performance.
| Study and setting | Reported result | How to read it |
|---|---|---|
| Qiankai Xu, Self-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer (September 2026); five benchmarks, with separate training and held-out tasks, plus five out-of-distribution benchmarks | Average improvements of 4.48 points on in-distribution benchmarks and 12.64 points on out-of-distribution benchmarks after the first evolution stage | Reported by the authors for this setup; not an independent replication. The same frozen model serves as solver and proposer. |
| Self-Harness; Terminal-Bench 2.0 held-out pass rates | MiniMax M2.5: 40.5% to 61.9%; Qwen3.5-35B-A3B: 23.8% to 38.1%; GLM-5: 42.9% to 57.1% | Each change is a model- and benchmark-specific result, not a general expected gain. |
| Jiahang Lin and coauthors, Agentic Harness Engineering; Terminal-Bench 2 | Pass@1 changed from 69.7% to 77.0% over ten iterations | The authors also report gains on three alternate model families without re-evolution; this supports transfer in their setup but does not establish universal cross-model transfer. |
| Wenbo Pan and coauthors, Retrospective Harness Optimization; SWE-Bench Pro | Pass rate changed from 59% to 78% after one optimization round | Microsoft Research’s June 2026 description says the method uses past trajectories, self-validation, self-consistency, and pairwise self-preference rather than external grading. A self-judged preference is not the same as independent held-out evaluation. |
One counterpoint is Rethinking the Evaluation of Harness Evolution for Agents. In Terminal-Bench 2.1 experiments, its authors report that harness evolution did not consistently outperform matched-budget parallel sampling or sequential refinement, and showed only marginal improvements on held-out tasks. The study argues that optimizing and evaluating on the same benchmark risks overfitting. Its abstract calls for fairer evaluation protocols, but the opened index page did not show an exact publication date or complete author metadata.
HarnessOpt-Bench offers a way to examine optimizer performance under tighter controls: it separates development, validation, and test partitions, hides held-out state in a trusted execution environment, meters resource use, and versions candidate harnesses. Its reported four-task evaluation found that optimizer performance varied by task and seed regime. Together, these results make evaluation design—not just the final score—central to judging a claimed improvement.
Rank #2
- 5-in-1 USB-C Hub: Experience comprehensive connectivity featuring a Power Delivery input, two USB-A 2.0 ports, a USB-A 3.0 port, and an HDMI port. (Note: The USB-C power delivery input port is only for connecting an external wall charger to power your laptop and cannot power peripheral devices.)
- 90W Pass-Through Charging: Achieve optimal charging with 90W pass-through power to your laptop, supported by a total input of 100W, with the hub reserving 10W for operational efficiency. (Note: Wall charger not included.)
- Quick Data Transfers: Accelerate your productivity with rapid data transfers using a high-speed 5Gbps USB 3.0 port and two 480Mbps USB 2.0 ports.
- 4K HDMI Display: Enhance your visual experience with a hub capable of delivering 4K resolution at 30Hz in both mirror and extend modes. Please note that this hub is compatible with MacBook (macOS 12 and newer), Windows 10 and 11, ChromeOS, and laptops equipped with DP Alt Mode and Power Delivery. Note: This device is not compatible with Linux.
- What You Get: Anker USB-C Hub (5-in-1, 4K HDMI), welcome guide, 18-month warranty, and our friendly customer service.
How to improve a harness without tuning to the test
-
Freeze the starting point
Keep the base model and starting harness fixed for the comparison. Record their versions and define the task-split boundaries before optimization begins. Otherwise, a score change cannot be attributed clearly to the harness.
-
Use outcome-linked traces to find recurring failures
Collect run traces with outcomes that can be checked, then look for repeated, concrete weaknesses. Self-Harness describes mining weaknesses from traces, proposing minimal candidate edits, and validating those proposals with regression tests. A small edit tied to a specific failure is easier to evaluate and roll back than a broad rewrite.
DriversCrashes, No Sound, or Screen Glitches?PerformanceWindows Errors? Fix Them Before They SpreadDriversOutdated Drivers Are Slowing You DownSpecial offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.Rank #3
Sale
Anker USB C Hub, 7in1 Multi-Port USB Adapter, 4K@60Hz USBC to HDMI Splitter- Sleek 7-in-1 USB-C Hub: Features an HDMI port, two USB-A 3.0 ports, and a USB-C data port, each providing 5Gbps transfer speeds. It also includes a USB-C PD input port for charging up to 100W and dual SD and TF card slots, all in a compact design.
- Flawless 4K@60Hz Video with HDMI: Delivers exceptional clarity and smoothness with its 4K@60Hz HDMI port, making it ideal for high-definition presentations and entertainment. (Note: Only the HDMI port supports video projection; the USB-C port is for data transfer only.)
- Double Up on Efficiency: The two USB-A 3.0 ports and a USB-C port support a fast 5Gbps data rate, significantly boosting your transfer speeds and improving productivity.
- Fast and Reliable 85W Charging: Offers high-capacity, speedy charging for laptops up to 85W, so you spend less time tethered to an outlet and more time being productive.
- What You Get: Anker USB-C Hub (7-in-1), welcome guide, 18-month warranty, and our friendly customer service.
-
Make every edit a testable hypothesis
For each candidate, log the component changed, the failure it is meant to address, the expected task outcomes, measured results, resource-cost change, and the accept-or-reject decision. Agentic Harness Engineering describes making components editable as files, distilling trajectories into an evidence corpus, and pairing edits with predictions checked against later outcomes. This turns an edit into an auditable claim rather than an unexplained score bump.
-
Protect validation and final test sets
Separate optimization, validation, and final test tasks. Do not reveal held-out examples, labels, or scores to the proposer. For stronger evidence of transfer, add domains or out-of-distribution benchmarks that were not used during evolution. Multiple task families can reduce the chance that a change merely encodes a narrow suite’s quirks.
Rank #4
Sale
UGREEN USB to USB C Adapter Combo 4-Pack, 10Gbps USB C Converter Space Gray- Dual Converters, Infinite Potential：Includes 2× USB C male to USB A female adapters and 2× USB A male to USB C female adapters. Perfect for a wide range of uses—tablets with Bluetooth keyboards, expand USB ports on macbook, and more. Two different converters for all your daily needs
- Next-Level 10Gbps & 3A Charging: No more slow 480Mbps, this usb to usb c adapter has a transfer speed of up to 10Gbps, allowing you to do more transferring in less time. This usb adapter fits both USB A and USB C charger, supporting up to 3A fast charging
- Upgraded Exquisite Craftsmanship: With an aluminum alloy housing and metal connector, the usbc to usb adapter is extremely durable and sturdy. Rigorously tested to withstand more than 10,000 times of plugging and unplugging, ensuring long-lasting performance
- Broad Compatible: The usb c to usb adapter widely supports all USB C/ USB A devices like laptops, tablets, cellphones, car chargers, and phone chargers. Such as compatible with MacBook Pro/Air 2023/2022, Thunderbolt 4/3 Devices,Apple MagSafe Watch 9/8/7/SE/Ultra, iPad Pro 2022/2021, Samsung Galaxy S23/S20/S10, and iPhone 17/16/15 Pro. Plug and play
- Please Note: To reach 10Gbps speed, keep the cable under 3.3 ft. For USB A Male to USB C adapters, try flipping the USB C connector. USB C Male to USB A adapters support bidirectional 10Gbps transfer within 3.3 ft
-
Screen edits and preserve regression checks
Review candidates for benchmark-specific logic, including references to task names, entities, answers, or hand-built special cases. Run regression tests, use an acceptance threshold that accounts for evaluation noise, and retain an auditable history of accepted and rejected changes. Google Research’s RRSI repository describes these safeguards, including an acceptance floor adjusted for noise and pruning components that no longer help.
-
Compare search against matched-budget baselines
Evaluate harness evolution against simple alternatives such as parallel sampling or sequential refinement, giving the methods comparable task feedback and inference budgets. Report resource use alongside success: extra search compute can explain apparent gains. Rethinking the Evaluation of Harness Evolution specifically tests matched-budget baselines, illustrating why a comparison with an unchanged harness alone can be insufficient.
PC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchSpecial offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.Best Value
Anker USB C Hub, 5-in-1 USBC to HDMI Splitter with 4K Display- 5-in-1 Connectivity: Equipped with a 4K HDMI port, a 5 Gbps USB-C data port, two 5 Gbps USB-A ports, and a USB C 100W PD-IN port. Note: The USB C 100W PD-IN port supports only charging and does not support data transfer devices such as headphones or speakers.
- Powerful Pass-Through Charging: Supports up to 85W pass-through charging so you can power up your laptop while you use the hub. Note: Pass-through charging requires a charger (not included). Note: To achieve full power for iPad, we recommend using a 45W wall charger.
- Transfer Files in Seconds: Move files to and from your laptop at speeds of up to 5 Gbps via the USB-C and USB-A data ports. Note: The USB C 5Gbps Data port does not support video output.
- HD Display: Connect to the HDMI port to stream or mirror content to an external monitor in resolutions of up to 4K@30Hz. Note: The USB-C ports do not support video output.
- What You Get: Anker 332 USB-C Hub (5-in-1), welcome guide, our worry-free 18-month warranty, and friendly customer service.
-
Report the scope, not just the headline score
State the model, harness version, benchmark version, task split, number of optimization rounds, budget, and whether results are held out or out of distribution. Include costs and regressions as well as success rates. Scores from separate papers should not be treated as a leaderboard unless their models, tasks, splits, and budgets are aligned.
How to judge whether an improvement is convincing
- Held-out success: Did the change help on tasks withheld from the optimizer, rather than only on the tasks used to propose it?
- Transfer: Does it work on a different domain, benchmark, or model family that was not part of evolution?
- Fair comparison: Does it beat simple search or test-time scaling when feedback and compute budgets are matched?
- Cost and reliability: Are gains worth added inference use, and did the change introduce regressions elsewhere?
- Auditability: Can another evaluator reconstruct what changed, why it was accepted, and how the held-out evaluation was protected?
Evidence for harness self-improvement is promising but mixed. The strongest claim a result supports is bounded by its model, harness, benchmark, split, and budget. A credible demonstration therefore combines controlled edits with independent evaluation and transparent accounting, rather than treating a benchmark score as proof that an agent has learned a broadly better way to work.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
