When reflections localize early errors, in-context search solves exp-small pass-rate problems with poly sequential attempts; otherwise it offers no asymptotic gain over parallel sampling, and the update is learnable and RLVR-optimal.
arXiv preprint arXiv:2503.17523 , year =
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 4roles
background 1polarities
background 1representative citing papers
Belief Engine is a configurable belief-update mechanism for multi-agent LLM systems that uses structured argument extraction and log-odds stance updates to make evidence-grounded deliberation inspectable and controllable.
An agentic forecaster with linguistic belief states, logit-space multi-trial shrinkage, and hierarchical Platt calibration achieves SOTA Brier Index on ForecastBench binary questions.
BASIL is a Bayesian probabilistic framework that separates sycophantic belief shifts from rational updating in LLMs and demonstrates its use on uncertainty-driven tasks along with mitigation via calibration and fine-tuning.
citing papers explorer
-
When Does In-Context Search Help? A Sampling-Complexity Theory of Reflection-Driven Reasoning
When reflections localize early errors, in-context search solves exp-small pass-rate problems with poly sequential attempts; otherwise it offers no asymptotic gain over parallel sampling, and the update is learnable and RLVR-optimal.
-
Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation
Belief Engine is a configurable belief-update mechanism for multi-agent LLM systems that uses structured argument extraction and log-odds stance updates to make evidence-grounded deliberation inspectable and controllable.
-
Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefs
An agentic forecaster with linguistic belief states, logit-space multi-trial shrinkage, and hierarchical Platt calibration achieves SOTA Brier Index on ForecastBench binary questions.
-
BASIL: Bayesian Assessment of Sycophancy in LLMs
BASIL is a Bayesian probabilistic framework that separates sycophantic belief shifts from rational updating in LLMs and demonstrates its use on uncertainty-driven tasks along with mitigation via calibration and fine-tuning.