arXiv AI

LLM-as-an-Improver: Turning Verification into Better Candidates

The paper introduces LLM-as-an-Improver, a method that uses verification feedback to enhance the candidate set in verifier-based selection. It proposes Verify–Repair–Reselect (VRR), which keeps the initial winner, generates three complementary alternatives (repaired versions of the winner and runner‑up, and a new approach), filters invalid or duplicate candidates, and then reselects the final answer. Experiments on code‑generation and reasoning benchmarks show that VRR outperforms fixed‑pool selection and can recover correct solutions even when the initial pool is entirely wrong.

Hugging Face Trending Papers

Jul 20

Verify, Repair, Repeat, or Stop? Robust Stopping for Noisy Verify-Repair Loops in LLM Agents

Verify-repair loops are a standard means for large language model (LLM) agents to correct faulty plans in code generation, mathematical reasoning, and tool use. When both the verifier and the repairer are noisy, repair can damage already-correct plans, and reported acceptance keeps rising while true validity falls, so existing methods lack a principled basis for deciding when repair should stop.

llms agents

arXiv AI

Jul 21

Verify, Repair, Repeat, or Stop? Robust Stopping for Noisy Verify-Repair Loops in LLM Agents

arXiv:2607. 17641v1 Announce Type: new Abstract: Verify-repair loops are a standard means for large language model (LLM) agents to correct faulty plans in code generation, mathematical reasoning, and tool use.

By Yitao Wu, Si Shen, Rui Yang, Hong Peng, Bin Hu

llms agents

arXiv AI

Jun 19

Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning

arXiv:2606. 19808v1 Announce Type: new Abstract: Test-time reasoning is increasingly used as a serving-time control knob, but extra reasoning is not uniformly valuable: it can repair failed attempts, waste compute on already-correct answers, or introduce harmful answer changes.

By Sajib Acharjee Dip, Dawei Zhou, Liqing Zhang

arXiv AI

Aug 7

Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning

arXiv:2608. 05643v1 Announce Type: new Abstract: Test-time scaling improves LLM reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollouts often repeat existing answer patterns instead of adding useful reasoning diversity.

By Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer, Lena Trigg, Ali Subhan, Muhammad Ali, Dean F. Hougen

llms reinforcement-learning

arXiv AI

Aug 20

Selection, Recombination, or a Fresh Solve? A Candidate-Free Control for Single-Pass Test-Time Aggregation

The paper investigates whether providing candidate solutions during test‑time aggregation improves or harms accuracy compared to a fresh solve that does not use any candidates. Using Qwen3‑4B on AIME‑2025 and HMMT‑2025, the authors find that conditioning on multiple correct candidates boosts accuracy (+0.290), while conditioning on an all‑wrong candidate pool reduces accuracy (−0.123); the effect for a single correct candidate remains unclear. The study also explores structured interventions and placebo controls, but the underlying mechanisms of these effects are not resolved.

By Guiv Farmanfarmaian

benchmarks

arXiv AI

2d ago

Which Self-Improvements Should We Trust? Reliable Self-Improvement When Agents Reuse Their Benchmarks

arXiv:2609.33180v2 Announce Type: replace-cross Abstract: As recursive self-improvement (RSI) rapidly advances, reliable evaluation becomes critical for guiding adaptive search. RSI typically relies...

By Xiaojing Sun, Yuhan Zeng, Zihua She, Xiao Wang

agents benchmarks

arXiv AI

Jul 7

LLM-as-a-Verifier: A General-Purpose Verification Framework

arXiv:2607. 05391v1 Announce Type: new Abstract: Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs.

By Jacky Kwok, Shulu Li, Pranav Atreya, Yuejiang Liu, Yixing Jiang, Chelsea Finn, Marco Pavone, Ion Stoica, Azalia Mirhoseini

llms agents reinforcement-learning robotics benchmarks

arXiv AI

Sep 1

Training-free LLM Verification via Recycling Few-shot Examples

arXiv:2506.17251v3 Announce Type: replace-cross Abstract: Although large language models (LLMs) have achieved remarkable performance, the inherent stochasticity of their reasoning processes and varyi...

By Dongseok Lee, Jimyung Hong, Dongyoung Kim, Jaehyung Kim

llms

arXiv AI

Jul 13

Diversifying to Verify: When Task-Equivalent Programs Differ in Verifiability

arXiv:2607. 09366v1 Announce Type: cross Abstract: Program verification is crucial for software correctness, but producing fully verified programs remains difficult in practice.

By Shirley Yu, Ruben Martins

llms benchmarks

arXiv AI

Aug 26

Evaluating Multiple LLM Generations with Validated Task Coverage

The paper introduces VTC-Bench, a five‑domain benchmark designed to evaluate multiple outputs from large language models (LLMs) by measuring Validated Task Coverage (VTC). VTC quantifies how many distinct, useful results are produced within a set number of attempts, using real‑data tasks that allow automatic, reproducible checks of output quality and task‑relevant distinctness without relying on model‑based judges. Experiments show that models which perform best on single‑draw quality do not always achieve the highest coverage, and simple output‑variation metrics fail to capture task‑relevant diversity, highlighting the importance of evaluating finite candidate sets directly.

By Florian Le Bronnec, Rio Yokota

llms benchmarks

Hugging Face Trending Papers

Jul 6

LLM-as-a-Verifier: A General-Purpose Verification Framework

Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs. In this work, we identify verification, the ability to determine the correctness of a solution, as a new scaling axis.

llms agents reinforcement-learning robotics benchmarks

arXiv Machine Learning

Aug 4

CARE: Context-Aware Ranking Evolution with Executable Scoring Programs for Budgeted Reaction Optimization

arXiv:2606. 14581v4 Announce Type: replace Abstract: High-throughput experimentation can evaluate many reaction conditions, yet combinatorial condition spaces still exceed the available experiment budget.

By Guanyu Liu, Weiyi Kong, Chao Tang, Zeyu Wang, Boer Zhang, Baiqing Li, Peiyu Zhang, Tianyu Shi

llms efficiency

Related stories