A familiar line of reasoning runs as follows: language models are flexible approximators trained under a strictly proper loss, so scale brings them closer to Solomonoff induction, and their predictive success is evidence of that approach. We apply known results from algorithmic information theory, universal prediction...
Luan Ozelim, Abicumaran Uthamacumaran, H. Zenil· 0 citations
Since compact, interpretable classifiers correspond to simple programs, it is natural to ask if LLM-based coding agents can be used to learn interpretable models from data. In this paper we present a simple harness that repeatedly prompts a coding LLM to produce the next rule in a rule set, given a sample of labeled ex...
Aditya Kumar, Cassandra A. Cohen, William W. Cohen· 0 citations
People often learn from others' demonstrations, and inverse reinforcement learning (IRL) techniques have realized this capacity in machines. In contrast, teaching by demonstration has been less well studied computationally. Here, we develop a Bayesian model for teaching by demonstration. Stark differences arise when de...
Mark K. Ho, Michael L. Littman, James MacGlashan et al.· 0 citations
On-policy self-distillation (OPSD) uses a self-teacher conditioned on privileged information to turn the sparse outcome signal of reinforcement learning with verifiable rewards (RLVR) into dense token-level supervision. Yet the teacher's advantage may depend on information unavailable to the student at inference, raisi...
Yu-Hang Yang, Ming-Xuan Xia, Chao-Nan Ye et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Group-relative reinforcement learning methods such as GRPO train large language model (LLM) agents by comparing rollouts for the same task. When every trajectory in a group fails with the same reward, relative advantages collapse toward zero, leaving no useful learning signal. A frozen teacher can recover from a studen...
Haoze Li, Peng Zhou, Peiyuan Wu et al.· 0 citations
Rule decisions such as content moderation, advertising compliance, and eligibility checks combine several conditions, exemptions, and missing-information cases, and an error can be fixed only once the failing condition is known. We introduce SemTree, a framework that represents a rule decision as a semantic decision tr...
This paper proposes a hybrid reinforcement learning trading framework integrating intraday market data with transformer-based financial sentiment signals. The system extracts sentiment dynamics and semantic event clusters from financial news and incorporates them into a PPO-based trading agent. Experiments on intraday...
Concept representations in diffusion models drift across network depth and denoising time, yet existing sparse autoencoders offer only per-block or per-timestep dictionaries, leaving no single feature dictionary for localization and intervention in the network. We present Shared Sparse Autoencoder (SharedSAE), which le...
Reinforcement learning with verifiable rewards improves mathematical reasoning when a final answer can be checked, but a correct answer does not certify the derivation behind it, and proof problems offer no answer to check. Replacing the check with a reasoning model as an in-loop verifier faces a fundamental obstacle:...
Hamed Mahdavi (Pennsylvania State University), Pouria Mahdavinia (Pennsylvania State University), Majid Farhadi (Google) et al.· 0 citations
Post-training large language models (LLMs) on two-player zero-sum games provides a verifiable reward, and the gains have been shown to transfer to general reasoning. Existing pipelines, however, rely on a handful of hand-written games and on advantage estimators tied to them, so both the supply of games and the advanta...
Weixian Waylon Li, Jiaxin Zhang, Han Zhou et al.· 0 citations
Flow matching learns how to transport noise toward data, but its mean prediction does not directly report the endpoint uncertainty remaining at an intermediate state. This paper introduces Posterior Flow Matching (PFM), a general generative modeling framework that learns conditional velocity means and componentwise var...
Chen-Rui Ma, Xi Xiao, Lin Zhao et al.· 0 citations
Self-evolving agents improve through repeated cycles of modification and evaluation. However, existing methods receive feedback on modifications only after costly evaluations, and aggregate scores may obscure distinctions between failures that require different repairs. We introduce predictive self-evolution through an...
Zi-Xuan Xie, Chang-Feng Xu, Yu-Hua Jiang et al.· 0 citations
