This framework organizes existing methods around five components: explicit state representation, transition structuring, validation and constraint enforcement, search and rollback, and uncertainty management, and yields a diagnostic hypothesis: interventions should be most effective when they target the error or uncertainty component implicated by an observed failure.
Abstract
Complex problem solving (CPS) with large language models (LLMs) is often framed as a matter of stronger reasoning or longer generation. Yet early-step error amplification, prompt brittleness, and failures to revise incorrect commitments are difficult to explain by missing knowledge or expressive capacity alone. This survey interprets CPS as a sequential estimation-and-decision problem over a latent solution state. A controller maintains a belief about an unobserved solution trajectory, updates it as noisy intermediate evidence arrives, and decides whether to commit, verify, branch, roll back, or abstain to minimize expected loss. Reasoning supplies candidate transitions and interpretations, whereas process control shapes and evaluates those proposals and regulates subsequent transitions and observations. Within this framework, we organize existing methods around five components: explicit state representation, transition structuring, validation and constraint enforcement, search and rollback, and uncertainty management. We also interpret evaluation metrics according to the statistical quantities they estimate. The framework further yields a diagnostic hypothesis: interventions should be most effective when they target the error or uncertainty component implicated by an observed failure. We distinguish systematic, stochastic, and irreducible error together with epistemic and aleatoric uncertainty, and call this alignment problem-control fit and its failure control mismatch. For example, additional sampling may reduce sampling variability while leaving a shared systematic error unchanged. This perspective clarifies what current methods estimate and control, what remains uncontrolled, and why reliable validation, targeted recovery, calibrated uncertainty, and matched-budget evaluation are central open problems.
This empirical study covers broad knowledge, symbolic reasoning, and competition mathematics, and it introduces an evaluation profile whose coordinates and simple functionals recover or bound common repeated-sampling metrics, and require compute accounting and uncertainty estimates that match the protocol.
It is proved that the LLM paired with the BSE is a sound Markov policy on the belief MDP induced by the underlying POMDP, and inherits the Bellman optimality guarantees of classical POMDP theory, provided the LLM is never exposed to the raw history.
Speculative Uncertainty (SU), a method that recovers a predictive failure signal for a black-box agent from its output tokens alone, with no access to logits, weights, activations, or repeated sampling, is presented.
A diagnostic framework is introduced that abstracts chain-of-thought reasoning as a trajectory through discrete latent reasoning states, yielding a positional taxonomy of six reasoning pathologies, each paired with a transition-grounded detection predicate and a matched inference-time controller that positions it as a...
Together, the survival and rationale analyses reveal distinct temporal reliability regimes and model-specific"failure fingerprints", offering an evaluation lens for diagnosing inconsistency in multi-turn agent behavior.
Igor Bogdanov, Olga Manakina, Chung-Horng Lung· 1 citation
Decision-Flow Sampling (DF-Sample), a training-free, data-free inference-time framework that constructs a hierarchical reasoning tree, scores terminal nodes for quality, and back-propagates utilities to inform each intermediate branching decision, indicating substantial latent reasoning potential in pretrained base mod...
Zhen-Dong Mi, Shao-Yi Huang· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 6, 2026
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.