An RL-guided MCTS proof search for Tamarin finds more and shorter proofs than standard search across 16 protocol models.
Title resolution pending
24 Pith papers cite this work, alongside 9,199 external citations. Polarity classification is still indexing.
24
Pith papers citing it
9,199
external citations · OpenAlex
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
TESSERA combines LLMs as local policy and evaluator with MCTS on knowledge graphs to compose mechanistic drug-disease explanations.
Bandit algorithms can be adapted to Tree MDPs by treating policies as arms with shared-data confidence bounds, achieving polynomial memory and instance-dependent bounds on sample complexity and regret that depend on terminal-state gaps rather than all policies.
AMBer applies reinforcement learning with physics feedback to automate construction of neutrino flavor models that minimize free parameters, validated on known cases and extended to a new symmetry group.
Introduces parametric open-source games as continuous analogues of program equilibria, proves equilibrium existence, and derives an exact coupling threshold for cooperation in symmetric 2x2 games under gradient ascent.
Improved upper bound α_3 ≤ 0.2953 for Witsenhausen's problem in dimension 3 via harmonic analysis, geometric fractional chromatic number, and a computer-searched 33-point set.
ARC-RL is a new suite of four MuJoCo continuous-control environments featuring game-inspired hexapod and quadruped morphologies, a single closed-form multi-component reward function, CPG demonstrators, and empirical comparisons of online and offline-to-online RL algorithms.
SimpleTES scales test-time evaluation in LLMs to discover state-of-the-art solutions on 21 scientific problems across six domains, outperforming frontier models and optimization pipelines with examples like 2x faster LASSO and new Erdos constructions.
Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.
Ranked preference modeling outperforms imitation learning for language model alignment and scales more favorably with model size.
Effective data transferred from pre-training to fine-tuning is described by a power law in model parameter count and fine-tuning dataset size, acting like a multiplier on the fine-tuning data.
The FIL Hypothesis claims that inductive biases outperform purely data-driven methods on GPU programming tasks with non-trivial feedback loops.
Introduces consensus objective aggregation for meta-optimization of scientific discovery and reports improved scaling and speedup for 3-SAT algorithm discovery using digital MemComputing machines.
DuDi is a dual-signal distillation method with cross-lingual verbalizer that improves multilingual SLM performance on SEA languages and outperforms baselines on SEA-HELM.
Introduces the VET framework to categorize and critique polarized AI narratives including hype, doom, denial, and normalcy.
RAT estimates Tikhonov-regularized natural policy gradients by rewriting them with the Woodbury identity, approximating the transformed advantage via randomized block Kaczmarz, and applying it as a vanilla policy gradient surrogate.
IFPV integrates multi-perspective hierarchical agents for generative planning with an adversarial cognitive simulation engine for verification, reporting 19.4% higher mission success, 41.7% lower cost versus LLM baseline, and 31.8% higher suppression versus rule-based validation in combat simulation
GIFT fine-tunes deep RL policies with a stability-focused reward to improve global stability while preserving task performance.
A two-stage OMR pipeline decodes symbol candidates into polyphonic score structures via topology recognition with probability-guided search.
Randomly masking a proposer's output vocabulary during training and generation sustains curriculum diversity and improves solver accuracy by +4.4 points at 8B in LLM co-evolution.
A survey of 87 agents for computer use and 33 datasets that introduces a three-dimensional taxonomy across domain, interaction, and agent perspectives and identifies six research gaps.
Supervised learning across AI systems vindicates a uniform error-driven associationism for cognition, though operating inside advanced computational structures beyond classical associationist models.
The chapter synthesizes the history of adaptive learning systems and examines how AI can provide instructional intelligence and real-time adaptivity in serious games while highlighting challenges such as explainability and limited long-term outcome data.
Advocates developing high-quality open-source scheduling software and linking observation planning with data analysis for future astronomical surveys.
citing papers explorer
-
Less Effort, Shorter Proofs: Reinforcement Learning for Security Protocol Analysis in Tamarin
An RL-guided MCTS proof search for Tamarin finds more and shorter proofs than standard search across 16 protocol models.
-
LLM-Guided Monte Carlo Tree Search over Knowledge Graphs: Composing Mechanistic Explanations for Drug-Disease Pairs
TESSERA combines LLMs as local policy and evaluator with MCTS on knowledge graphs to compose mechanistic drug-disease explanations.
-
On-line Learning in Tree MDPs by Treating Policies as Bandit Arms
Bandit algorithms can be adapted to Tree MDPs by treating policies as arms with shared-data confidence bounds, achieving polynomial memory and instance-dependent bounds on sample complexity and regret that depend on terminal-state gaps rather than all policies.
-
Towards AI-assisted Neutrino Flavor Theory Design
AMBer applies reinforcement learning with physics feedback to automate construction of neutrino flavor models that minimize free parameters, validated on known cases and extended to a new symmetry group.
-
Parametric Open Source Games
Introduces parametric open-source games as continuous analogues of program equilibria, proves equilibrium existence, and derives an exact coupling threshold for cooperation in symmetric 2x2 games under gradient ascent.
-
Improved bounds for the double cap conjecture
Improved upper bound α_3 ≤ 0.2953 for Witsenhausen's problem in dimension 3 via harmonic analysis, geometric fractional chromatic number, and a computer-searched 33-point set.
-
ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders
ARC-RL is a new suite of four MuJoCo continuous-control environments featuring game-inspired hexapod and quadruped morphologies, a single closed-form multi-component reward function, CPG demonstrators, and empirical comparisons of online and offline-to-online RL algorithms.
-
Evaluation-driven Scaling for Scientific Discovery
SimpleTES scales test-time evaluation in LLMs to discover state-of-the-art solutions on 21 scientific problems across six domains, outperforming frontier models and optimization pipelines with examples like 2x faster LASSO and new Erdos constructions.
-
Language Models (Mostly) Know What They Know
Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.
-
A General Language Assistant as a Laboratory for Alignment
Ranked preference modeling outperforms imitation learning for language model alignment and scales more favorably with model size.
-
Scaling Laws for Transfer
Effective data transferred from pre-training to fine-tuning is described by a power law in model parameter count and fine-tuning dataset size, acting like a multiplier on the fine-tuning data.
-
The FIL Hypothesis: Inductive Biases Help with Kernel Engineering
The FIL Hypothesis claims that inductive biases outperform purely data-driven methods on GPU programming tasks with non-trivial feedback loops.
-
Scientific discovery as meta-optimization: a combinatorial optimization case study
Introduces consensus objective aggregation for meta-optimization of scientific discovery and reports improved scaling and speedup for 3-SAT algorithm discovery using digital MemComputing machines.
-
DuDi: Dual-Signal Distillation with Cross-Lingual Verbalizer
DuDi is a dual-signal distillation method with cross-lingual verbalizer that improves multilingual SLM performance on SEA languages and outperforms baselines on SEA-HELM.
-
VET: A Framework for Analyzing AI Discourse
Introduces the VET framework to categorize and critique polarized AI narratives including hype, doom, denial, and normalcy.
-
Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation
RAT estimates Tikhonov-regularized natural policy gradients by rewriting them with the Woodbury identity, approximating the transformed advantage via randomized block Kaczmarz, and applying it as a vanilla policy gradient surrogate.
-
IFPV: An Integrated Multi-Agent Framework for Generative Operational Planning and High-Fidelity Plan Verification
IFPV integrates multi-perspective hierarchical agents for generative planning with an adversarial cognitive simulation engine for verification, reporting 19.4% higher mission success, 41.7% lower cost versus LLM baseline, and 31.8% higher suppression versus rule-based validation in combat simulation
-
GIFT: Global stabilisation via Intrinsic Fine Tuning
GIFT fine-tunes deep RL policies with a stability-focused reward to improve global stability while preserving task performance.
-
From Image to Music Language: A Two-Stage Structure Decoding Approach for Complex Polyphonic OMR
A two-stage OMR pipeline decodes symbol candidates into polyphonic score structures via topology recognition with probability-guided search.
-
Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution
Randomly masking a proposer's output vocabulary during training and generation sustains curriculum diversity and improves solver accuracy by +4.4 points at 8B in LLM co-evolution.
-
A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions
A survey of 87 agents for computer use and 33 datasets that introduces a three-dimensional taxonomy across domain, interaction, and agent perspectives and identifies six research gaps.
-
The New Associationism: Lessons from Deep Learning
Supervised learning across AI systems vindicates a uniform error-driven associationism for cognition, though operating inside advanced computational structures beyond classical associationist models.
-
AI-Enabled Serious Games: Integrating Intelligence and Adaptivity in Training Systems
The chapter synthesizes the history of adaptive learning systems and examines how AI can provide instructional intelligence and real-time adaptivity in serious games while highlighting challenges such as explainability and limited long-term outcome data.
-
Scheduling Discovery in the 2020s
Advocates developing high-quality open-source scheduling software and linking observation planning with data analysis for future astronomical surveys.