AutoTTS discovers width-depth test-time scaling controllers through agentic search in a pre-collected trajectory environment, yielding better accuracy-cost tradeoffs than hand-designed baselines on math reasoning tasks at low cost.
hub Canonical reference
In: International Conference on Machine Learning (ICML) (2024), https://arxiv.org/abs/2401.02051
Canonical reference. 75% of citing Pith papers cite this work as background.
22
Pith papers citing it
Background
75% of classified citations
hub tools
citation-role summary
background 6
baseline 2
citation-polarity summary
representative citing papers
EPB distills NCO models into evolving program portfolios via LLM-driven textual-numerical optimization, matching original performance while exposing stage-dependent heuristic-like behavior.
FrontierOR benchmark shows frontier LLMs outperform Gurobi on solution quality and efficiency in only 31% of one-shot cases and 50% with test-time evolution on hard large-scale optimization tasks.
Latent Heuristic Search performs continuous optimization over learned embeddings of heuristics, using normalizing flows and LLM prompting to discover competitive solvers for TSP, CVRP, KSP, and OBP.
SMCEvolve applies Sequential Monte Carlo sampling to LLM program search with adaptive resampling, mutation mixtures, and convergence control, delivering finite-sample complexity bounds and benchmark gains over prior systems.
LLM-generated combinatorial solvers achieve highest correctness when the model formalizes problems for verified backends rather than attempting to optimize search, which often causes regressions.
A code-graph and correction-based LLM search framework outperforms full-algorithm generation at equal token budgets on three combinatorial optimization problems.
AHD Agent trains a 4B-parameter LLM via agentic RL to actively use tools for automatic heuristic design, matching or exceeding larger baselines across eight domains with fewer evaluations.
A VOI-based controller for dual inference budgets improves multi-hop QA performance by prioritizing search actions and selectively finalizing answers.
LaF-MCTS uses LLM-assisted flexible MCTS with a three-tier hierarchy, semantic pruning, and branch regrowth to automatically compose decomposition-enhanced CVRP solvers that outperform state-of-the-art methods on CVRPLib benchmarks.
C-TRAIL combines LLM commonsense with a dual-trust mechanism and Dirichlet-weighted Monte Carlo Tree Search to improve trajectory planning accuracy and safety in autonomous driving.
AlphaEvolve is an LLM-orchestrated evolutionary coding agent that discovered a 4x4 complex matrix multiplication algorithm using 48 scalar multiplications, the first improvement over Strassen's algorithm in 56 years, plus optimizations for Google data centers and hardware.
An LLM evolutionary framework generates executable heuristics for frame-level QP adaptation in VVenC that improve rate-distortion performance over fixed-QP and Lagrangian baselines.
RACL lets a reasoning agent discover and apply control rules to a metaheuristic by observing operational memory and testing bounded interventions, shown on vehicle routing with reported cost improvements over baselines.
MeEvo cyclically couples natural and metacognitive evolution in LLM-based automatic heuristic design to achieve stronger performance and lower variance on optimization problems.
UH-NAS uses LLMs as evolutionary operators in a swappable-backend NAS to co-optimize neural architectures for accuracy and inference energy on physical hardware such as optical MZIs, producing more diverse and robust designs than baselines.
LLM agent translates user prompts into model patches and selects primal-aware re-optimization techniques for large-scale dynamic problems, shown on supply-chain and exam-scheduling cases.
HMACE deploys Proposer, Generator, Evaluator, and Reflector agents in an evolutionary loop to generate and refine heuristics for NP-hard problems, reporting lower optimality gaps and token costs than baselines on TSP and Online BPP.
COEVO unifies correctness and multi-objective PPA optimization in a single evolutionary loop for LLM RTL generation, reporting 97.5% and 94.5% Pass@1 on VerilogEval/RTLLM benchmarks plus best PPA on 43 of 49 designs.
ResearchEVO automates the discover-then-explain cycle by evolving algorithms via fitness-driven LLM co-evolution and generating grounded, anti-hallucination research papers through sentence-level RAG.
TransGP uses a task-conditioned Transformer to guide genetic programming toward elite heuristics and generate task-specific rules for multitask dynamic flexible job shop scheduling, outperforming standard GP and handcrafted methods in experiments.
EvoGens uses rank-based mutation, semantic-aware crossover, and lightweight evaluation to evolve populations of LLM-generated scientific ideas, boosting novelty and diversity metrics.
citing papers explorer
-
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
AutoTTS discovers width-depth test-time scaling controllers through agentic search in a pre-collected trajectory environment, yielding better accuracy-cost tradeoffs than hand-designed baselines on math reasoning tasks at low cost.
-
Inference-Time Budget Control for LLM Search Agents
A VOI-based controller for dual inference budgets improves multi-hop QA performance by prioritizing search actions and selectively finalizing answers.
-
C-TRAIL: A Commonsense World Framework for Trajectory Planning in Autonomous Driving
C-TRAIL combines LLM commonsense with a dual-trust mechanism and Dirichlet-weighted Monte Carlo Tree Search to improve trajectory planning accuracy and safety in autonomous driving.
-
AlphaEvolve: A coding agent for scientific and algorithmic discovery
AlphaEvolve is an LLM-orchestrated evolutionary coding agent that discovered a 4x4 complex matrix multiplication algorithm using 48 scalar multiplications, the first improvement over Strassen's algorithm in 56 years, plus optimizations for Google data centers and hardware.
-
HMACE: Heterogeneous Multi-Agent Collaborative Evolution for Combinatorial Optimization
HMACE deploys Proposer, Generator, Evaluator, and Reflector agents in an evolutionary loop to generate and refine heuristics for NP-hard problems, reporting lower optimality gaps and token costs than baselines on TSP and Online BPP.
-
TransGP: Task-Conditioned Transformer-Guided Genetic Programming for Multitask Dynamic Flexible Job Shop Scheduling
TransGP uses a task-conditioned Transformer to guide genetic programming toward elite heuristics and generate task-specific rules for multitask dynamic flexible job shop scheduling, outperforming standard GP and handcrafted methods in experiments.