Pith. sign in

REVIEW 8 cited by

OPT-BENCH: Evaluating LLM Agent on Large-Scale Search Spaces Optimization Problems

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.10764 v1 pith:KDQNKFPE submitted 2025-06-12 cs.AI cs.LG

classification cs.AIcs.LG
keywords optimizationopt-benchproblemsreasoningtasksagentscomplexdiverse
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) have shown remarkable capabilities in solving diverse tasks. However, their proficiency in iteratively optimizing complex solutions through learning from previous feedback remains insufficiently explored. To bridge this gap, we present OPT-BENCH, a comprehensive benchmark designed to evaluate LLM agents on large-scale search space optimization problems. OPT-BENCH includes 20 real-world machine learning tasks sourced from Kaggle and 10 classical NP problems, offering a diverse and challenging environment for assessing LLM agents on iterative reasoning and solution refinement. To enable rigorous evaluation, we introduce OPT-Agent, an end-to-end optimization framework that emulates human reasoning when tackling complex problems by generating, validating, and iteratively improving solutions through leveraging historical feedback. Through extensive experiments on 9 state-of-the-art LLMs from 6 model families, we analyze the effects of optimization iterations, temperature settings, and model architectures on solution quality and convergence. Our results demonstrate that incorporating historical context significantly enhances optimization performance across both ML and NP tasks. All datasets, code, and evaluation tools are open-sourced to promote further research in advancing LLM-driven optimization and iterative reasoning. Project page: \href{https://github.com/OliverLeeXZ/OPT-BENCH}{https://github.com/OliverLeeXZ/OPT-BENCH}.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games

    cs.CV 2026-06 unverdicted novelty 7.0 of 10

    RNG-Bench evaluates MLLMs on hidden-observation reconstruction in non-Markov games, finds forgetting as the dominant error source, and shows fine-tuning on optimal rollouts improves performance with transfer to other ...

  2. PEARL: Solver-in-the-Loop Interactive Optimization Modeling from Natural Language

    cs.AI 2026-05 reject novelty 7.0 of 10

    Training an LLM as a multi-turn agent that runs and repairs solver code raises verified optimization solve rates, with the 4B PEARL model outperforming DeepSeek-V3.2-685B in aggregate.

  3. MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    MiniOpt is an RL framework that decomposes optimization reasoning into modeling and solver generation, achieving top solving accuracy for models under 10B parameters across diverse problem types using OptReward and op...

  4. What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents

    cs.AI 2026-05 unverdicted novelty 6.0 of 10

    SERL selectively reweights learning using task success and environment feedback to reach 90.0% success on ALFWorld and 80.1% on WebShop, outperforming RL and distillation baselines.

  5. Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs

    cs.AI 2026-05 unverdicted novelty 6.0 of 10

    OPT-BENCH trains LLMs on NP-hard optimization via quality-aware RLVR, achieving 93.1% success rate and 46.6% quality ratio on Qwen2.5-7B while outperforming GPT-4o and transferring gains to other domains.

  6. What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search

    cs.CL 2026-04 unverdicted novelty 6.0 of 10

    Strong LLM optimizers act as local refiners with incremental improvements and semantic localization, while weaker ones show large drift and stagnation; solution novelty predicts success only when searches stay localiz...

  7. MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources

    cs.LG 2026-06 unverdicted novelty 5.0 of 10

    MiniOpt trains LLMs under 10B parameters via RL with OptReward to model and solve general optimization problems, reporting highest average solving accuracy among comparable models.

  8. Large Language Models for Operations Research: A Comprehensive Survey

    math.OC 2026-05 unverdicted novelty 2.0 of 10

    A survey compiling roles, applications, benchmarks, challenges, and future directions for large language models in operations research.

Pith tools