OptiCom is proposed, a unified framework that represents LLM-driven optimizers within a shared configuration space: C=(A,Q,O,E,M,S), corresponding to artifact, query, operator, evaluation, memory, and strategy, corresponding to artifact, query, operator, evaluation, memory, and strategy.
Abstract
Large language models (LLMs) are increasingly deployed to solve complex scientific and practical problems via iterative optimization. However, dynamically coordinating diverse search mechanisms as candidate quality, failure modes, and resource budgets evolve remains a critical open challenge. Targeted empirical diagnostics reveal that mechanism effectiveness is highly state-dependent. Motivated by this, we analyze how individual decisions drive final outcomes, decomposing the expected terminal improvement under a shared budget into cumulative decision opportunities minus cumulative selection losses. Guided by this opportunity-loss theoretical foundation, we propose OptiCom, a unified framework that represents LLM-driven optimizers within a shared configuration space: C=(A,Q,O,E,M,S), corresponding to artifact, query, operator, evaluation, memory, and strategy. Operating within this space, a fast LLM-based Optimization Controller dynamically composes immediate mechanisms through structured Action Packages, while a slower Strategy Adapter refines long-term selection preferences, operator weights, and templates based on accumulated trajectory feedback. Comprehensive evaluations across 32 benchmark groups demonstrate the superiority of framework: OptiCom achieves an average Max-score rank of 1.72 among 14 evaluated configurations, securing the top score in 23 groups. Ultimately, these results highlight the broad applicability and high extensibility of OptiCom as a general-purpose paradigm for robust LLM test-time scaling.
StateTune is presented, which reformulates LLM-assisted EDA tuning as a closed-loop, state-carrying process that achieves the strongest final hypervolume on all six benchmark blocks, showing a stable improvement in frontier quality across the full matrix.
Kunlong Li, Shang-Shang Yao, Su Zheng et al.· 0 citations
StarHarness offers a practical way to reduce persistent model-environment mismatch in tool-rich enterprise tasks by stratifying tasks according to baseline failure behavior, separating proposer-visible search tasks from proposer-hidden selection tasks, and reserves held-out tasks for evaluating generalization.
Esakkivel Esakkiraja, D. Akhiyarov, Vikas Yadav et al.· 1 citation
LLM-Orch is an integrated, serverless system for coordination based on large-scale language models that interprets operator instructions using contextual reasoning and continuously refines coordination decisions based on feedback from execution and ensures the stability and adaptability of the system in the long term.
Dynamic Retrieval-based Policy Generation (DRPG) is proposed, a framework that integrates memory-based retrieval with a dynamic policy generator, leveraging historical data and environment feedback to produce task-specific policies for continual LLM improvement.
A unified taxonomy of agent context compression along three dimensions is introduced: compression target (what is compressed), compression mechanism (how it is transformed and retained), and control policy (who decides when compression is triggered).
Evolutionary approaches to LLM-driven discovery often generate new programs from a small set of selected ancestors. This keeps contexts manageable but can omit useful evidence from other experiments, whereas including the full experimental history produces long, redundant contexts. We introduce a simple, single-agent d...
Bo Yuan, Wenqian Ye, Ze-Lin Zhao et al.· 0 citations