Meta-reasoning, an inference-time harness that makes agentic meta-reasoning an explicit and structured reasoning process, keeps improving over the tested budget ranges where direct control plateaus, though its overhead can hurt at small budgets.
Abstract
As agents take on longer and more complex problems, controlling the execution becomes a task in its own right. Each step in the run brings new control choices, like which partial work to build on, whether to start fresh, or when to stop. We introduce agentic meta-reasoning, an inference-time harness that makes these choices an explicit and structured reasoning process. Workers carry out the task-level computation, while a controller consolidates what the run has established, explores next options, assesses what each option is worth under the remaining budget, and dispatches the chosen work with context drawn from persistent memory. Between decisions the controller carries only a compact account of the run rather than replaying its full history. Our baselines span production coding agents and research harnesses, together with a Direct Control Agent using the same workers and compute budget allowance. On ProgramBench, which tests long-horizon agentic capability through program reconstruction, meta-reasoning achieves 71.5% with GPT-5.5 against 58.0% for Codex; with Opus 4.8 it achieves 67.2% against 65.5% for Claude Code. On the other benchmarks, spanning abstract reasoning, multi-domain long-horizon reasoning, and proof generation, it gains between 3.6 and 4.2 points over direct control, averaged across three frontier models. It keeps improving over the tested budget ranges where direct control plateaus, though its overhead can hurt at small budgets. Artifact-graph analysis reveals more reuse of earlier work, higher coverage of correct solutions in most settings, and nonuniform gains in final selection. These results indicate that spending computation on structured control becomes more important as agents scale to longer runs.
Long-horizon research agents must decide both how to investigate and what to investigate next as evidence accumulates. This is hard to learn because such decisions are sparse in long execution traces, and their consequences may emerge several investigations later. We introduce Meta-reasoning for Iterative Research Agen...
Ankur Samanta, Yonathan Efroni, Paul Sajda et al.· 0 citations
State of Thought is proposed, a new reasoning paradigm that enables endogenous reasoning in LLMs, with the model's internal reasoning state governing how reasoning unfolds, and provides a generalizable and efficient alternative to existing test-time reasoning paradigms.
Z. Gong, Yi-Kun Hou, Zi-Hao Zeng et al.· arXiv.org· 0 citations
Agent evaluations should be evaluated as configurable systems themselves, and that some desired behaviors are more effectively implemented in the system than requested through prompting, according to a new benchmark of four scientific tasks.
Luis Wiedmann, Leander Girrbach, Cordelia Schmid et al.· 0 citations
Dual-process agents pair a fast policy with a slow deliberative model. In real-time settings the slow model usually runs continuously; in turn-based agents and robot planners it is invoked on events such as uncertainty or a detected failure. We study a fast learned actor that takes every decision and hands control to a...
Large language model (LLM) agents can now undertake increasingly complex tasks, but the way they organize interaction history into memory does not ensure a coherent understanding of the current world. We introduce PoS, an inference-time framework that constructs and continually maintains explicit belief states as the a...
Yu Luo, Jia-Min Jiang, Yi-Min Zuo et al.· 1 citation
Analysis shows that BRANCH's advantage arises not only from exploring multiple reasoning paths, but also from recovering from truncation: its gains strongly correlate with the baseline rate of empty, budget-exhausted outputs, weakening the hypothesis that different problems require routing among test-time reasoning ope...
Sheng Zhang, Xiao-Min Wu, Xi-Yang Wu et al.· 0 citations