The study evaluates whether prompt optimizers that improve a target metric inadvertently violate other unscored requirements. Using GEPA, MIPROv2, and TextGrad on HotpotQA, SQuAD 2.0, and IFEval, the authors find that all three optimizers cause regressions in unscored aspects such as citation validity and output format, especially on HotpotQA. However, a post‑hoc analysis shows that many violations stem from early termination of responses under a 200‑token limit, and with a 1,024‑token cap the regressions largely disappear, indicating the side effects are narrower than expected.
arXiv:2608. 10471v1 Announce Type: new Abstract: Prompt optimizers automate the search for prompts that improve language-model performance, but existing methods rely on a predefined optimization procedure: the algorithm determines which candidates to explore and how the search progresses, while the language model generates or refines prompt proposals.
arXiv:2610.19084v1 Announce Type: new Abstract: Automatic prompt optimization (APO) uses feedback from model responses to improve prompts automatically. However, its effectiveness is usually measured...
ESPO (Error-Structured Prompt Optimization) addresses prompt bloat in evolutionary prompt optimizers by separating optimization into Diagnose, Propose, and Select phases. It clusters training errors, generates diverse candidates, and applies bootstrap stability selection, achieving a 3.76‑point accuracy gain over GEPA on seven NLP benchmarks while producing 47% shorter prompts. Cross‑model tests on four additional student models confirm ESPO’s superior average accuracy, notably improving Qwen3 GSM8K from 15.00% to 91.40%.
The paper introduces BudgetAPO, a single‑stage prompt optimizer designed for tight‑budget scenarios where only a few hundred model calls are feasible. BudgetAPO adapts the evaluation slice size to each task’s noise level, uses a fixed slice to turn accept/reject decisions into paired comparisons, and applies a reflective operator to jointly rewrite reasoning strategy and output format. Across seven benchmarks and five subject models, BudgetAPO outperforms existing methods, ranking first on every subject and requiring far fewer calls to achieve comparable or superior performance.
arXiv:2606. 21641v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have been proposed as hyperparameter-optimization (HPO) advisors that "warm-start" search from prior knowledge, proposing strong configurations in very few evaluations.
ESPO (Error-Structured Prompt Optimization) addresses prompt bloat in evolutionary prompt optimizers by splitting the optimization process into Diagnose, Propose, and Select phases. It clusters training errors into structural patterns, generates diverse candidate prompts through four complementary strategies, and applies bootstrap stability selection. Across seven NLP benchmarks, ESPO improves average accuracy by +3.76 pp over GEPA, produces prompts 47 % shorter, and achieves higher accuracy on four additional student models, with the largest gain on Qwen3 GSM8K.
arXiv:2606. 09410v1 Announce Type: new Abstract: Prior work treats structured output as a reasoning tax, but this framing is incomplete: the cost of formatting depends strongly on a model's spare capacity.
arXiv:2608. 13329v1 Announce Type: new Abstract: A model that behaves differently when it senses it is being tested would undermine the evaluations we rely on, so recent work has sought to read that sense directly from a model's activations.
The paper investigates why large‑language‑model coding agents rarely request a second chunk of tool output, focusing on the precision‑at‑1 rate ($p_1$) of the gold item appearing first in the first chunk. In a benchmark of 500 software‑engineering tasks, the authors compare six value functions and find that increasing $p_1$ does not systematically improve downstream accuracy; the agent can recover the correct answer from any position within the chunk. Adding file‑metadata signals to a keyword scorer actually reduces $p_1$, while a parameter‑free keyword scorer improves $p_1$ but still fails to boost overall accuracy.
The paper examines how budgeted context projection can reduce the length of individual requests while affecting whether an agent completes within its budget. By analyzing a recorded ReVerPi source‑reading campaign, the authors show that retaining all intervention boundaries reveals trade‑offs that are obscured when a capped first continuation prevents companion runs, and they quantify success differences across various task subsets. The study highlights the importance of accounting for every boundary, preserving unknown outcomes, and separating completion from resource use in adaptive evaluation campaigns.
arXiv:2606. 15887v1 Announce Type: cross Abstract: Large language model (LLM) systems are increasingly proposed to assist peer review, yet most evaluations judge the prose of machine-generated review text, not the validity of the numeric score a system assigns.
The paper introduces a benchmark for evaluating whether off‑the‑shelf small language models (SLMs) can reliably perform microtasks that support a large language model (LLM) planner, such as auto‑approving shell commands, writing memory, selecting tools, and ranking past turns. Using fixed prompts and confidence‑interval‑aware eligibility thresholds, the authors test several Qwen3 models (0.6/1.7/4/8 B) in FP16 with no tuning and find that none of the 16 configurations meet the eligibility criteria. Quantization to 4‑bit precision further degrades performance, with the eligibility gap tracking model size rather than precision, and the issue persists across different models (e.g., Llama‑3.x) and prompt variations.