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 benchmarks.
arXiv preprint arXiv:2506.10764 (2025)
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
dataset 1polarities
background 1representative citing papers
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.
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.
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 localized around high-performing regions.
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.
A survey compiling roles, applications, benchmarks, challenges, and future directions for large language models in operations research.
citing papers explorer
-
Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games
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 benchmarks.
-
What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents
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.
-
Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs
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.
-
What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search
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 localized around high-performing regions.
-
MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources
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.
-
Large Language Models for Operations Research: A Comprehensive Survey
A survey compiling roles, applications, benchmarks, challenges, and future directions for large language models in operations research.