The paper introduces EvalCEGAR, a method that automatically evolves a metric for evaluating AI-generated answers by iteratively refining a pool of small Python operators that flag potential defects. By using counterexample-guided abstraction refinement, the system identifies pairs of answers that score identically but differ in correctness, prompting the metric to broaden its scope rather than resample. On benchmark datasets, the evolved 55‑line operator closes a significant portion of the performance gap compared to hand‑written metrics and outperforms a large‑language‑model judge that incurs a cost per candidate.
By Xing Zhang, Yanwei Cui, Guanghui Wang, Zhihao Lin, Peiyang He
SiLR introduces a structure‑preserving admission and process reward mechanism for large language model (LLM) tool agents. Unlike traditional scalar‑score gates that can trap agents in plateau trajectories, SiLR shadow‑executes each proposal and admits it based on a product order over branch‑level violation states, ensuring safe and recoverable actions. Experiments on Gym‑ANM and CityLearn benchmarks show SiLR consistently recovers all multi‑action episodes and outperforms scalar gates, while also providing a robust reward signal for policy learning.
By Chenyu Zhou, Qiliang Jiang, Shuning Wu, Xu Zhou
arXiv:2603. 23420v2 Announce Type: replace Abstract: If autoresearch is itself a form of research, then autoresearch can be applied to research itself.
By Yaonan Qu, Meng Lu
arXiv:2606. 16999v1 Announce Type: cross Abstract: Frozen small code models ( =45.
By Mehmet Iscan
arXiv:2606. 01667v1 Announce Type: new Abstract: Test-time scaling has become a major way to improve large language model reasoning, but its orchestration has remained designer-engineered: a fixed sample budget, a fixed refinement loop, a fixed scoring rule, or a fixed search policy decides how compute is spent, leaving the model in charge of solving but not of orchestration.
By Peijia Qin, Qi Cao, Pengtao Xie
APEX-EM is a non‑parametric experience memory that stores full procedural‑episodic traces in a typed Procedural Knowledge Graph and retrieves them via semantic search, structural‑signature matching, and graph traversal. It uses a Plan‑Retrieve‑Generate‑Iterate‑Ingest workflow to produce, quality‑gate, and commit experiences, indexing both successes and failures so the agent learns what to reuse and what to avoid. Evaluations on five benchmarks with a shared GPT‑4o backbone show significant performance gains, such as +7.6 pp on BigCodeBench transfer and +1.4 pp on Lifelong Agent Bench, demonstrating that the memory adds to model capability rather than replacing it.
By Pratyay Banerjee, Masud Moshtaghi, Ankit Chadha
arXiv:2608. 15979v1 Announce Type: new Abstract: Large language models produce outputs presented as discoveries - new proofs, conjectures, or molecules.
By Eric Xie, Wenqian Ye, Aidong Zhang
LLM‑BabyBench transforms the BabyAI gridworld into a fully observable, purely textual setting that isolates planning as the sole source of failure. By serialising the entire grid, providing formal instructions, and validating actions deterministically, the benchmark introduces the PPD suite—Predict, Plan, and Decompose tasks—each scored with metrics that separate mission understanding from sequencing. Across a range of large language models, simulation accuracy is high while planning success drops sharply beyond a model‑specific horizon, revealing that plan length—not grid size—drives failure and that models often commit to a single corridor‑shaped route without backtracking.
By Idriss Malek, Omar Choukrani, Daniil Orel, Anh Duy Le Dinh, Zhuohan Xie, Zangir Iklassov, Martin Tak\'a\v{c}, Salem Lahlou
arXiv:2607. 18642v1 Announce Type: new Abstract: Mined code corpora are abundant but uncontrolled: a snippet's semantics, surface "messiness," and difficulty are whatever the wild contained; there is no known-optimal reference to grade against; and any public sample may already sit in a model's training set.
By Yuxiang Ji
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.
By Tatiana Petrova, Andrei Mazniak, Radu State
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.
By Carson Rodrigues, Oysturn Vas, Isaiah Abner DCosta, Nithish Kumar Prabhakaran
arXiv:2609.37356v1 Announce Type: new
Abstract: Generating optimization instances that are both feasible and computationally challenging is crucial for benchmarking solvers and training learning-base...
By Jitin Singla, Parikshit Pareek, Pratik Jawanpuria, Parag Singla