Tootfinder

Fusing Rewards and Preferences in Reinforcement Learning
Sadegh Khorasani, Saber Salehkaleybar, Negar Kiyavash, Matthias Grossglauser
https://arxiv.org/abs/2508.11363 https://…

Fusing Rewards and Preferences in Reinforcement Learning
We present Dual-Feedback Actor (DFA), a reinforcement learning algorithm that fuses both individual rewards and pairwise preferences (if available) into a single update rule. DFA uses the policy's log-probabilities directly to model the preference probability, avoiding a separate reward-modeling step. Preferences can be provided by human-annotators (at state-level or trajectory-level) or be synthesized online from Q-values stored in an off-policy replay buffer. Under a Bradley-Terry model, we p…

Strategic Cyber Defense via Reinforcement Learning-Guided Combinatorial Auctions
Mai Pham, Vikrant Vaze, Peter Chin
https://arxiv.org/abs/2509.10983 https://

Strategic Cyber Defense via Reinforcement Learning-Guided Combinatorial Auctions
Cyber defense operations increasingly require long-term strategic planning under uncertainty and resource constraints. We propose a new use of combinatorial auctions for allocating defensive action bundles in a realistic cyber environment, using host-specific valuations derived from reinforcement learning (RL) Q-values. These Q-values encode long-term expected utility, allowing upstream planning. We train CAFormer, a differentiable Transformer-based auction mechanism, to produce allocations tha…

Vom alten Glanz als wichtiger Industriestandort ist nicht mehr viel übrig. Ich war ja erst vor 2.5 Jahren das erste man hier, meine Schwester und ihr Mann schon kurz nach der samtenen Revolution. Allerdings sah damals auch Prag noch ganz anders aus als heute.
Auf jeden Fall scheint sich in letzter Zeit viel zu tun, im Zentrum der Stadt ist wohl vieles gegangen, es wird fleissig renoviert und investiert.
Hier übrigens über Hotel. 5 Minuten vom Bahnhof, mit Brauerei.

Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundaries
Marius Dragoi, Ioana Pintilie, Florin Gogianu, Florin Brad
https://arxiv.org/abs/2510.08325 https://

Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundaries
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm to improve Large Language Models on reasoning tasks such as coding, math or logic. To assess the reasoning boundary (the fraction of problems a model can solve) researchers often report Pass@k at large sampling budgets. Recent results reveal a crossover phenomenon: while RLVR models outperform the base model at small k values, the base model usually outperforms them when sampling a very large number of comp…

Anthropic raised a $13B Series F led by Iconiq at a $183B post-money valuation, up from $61.5B in March 2025, and says it has a $5B revenue run-rate (Anthropic)
https://www.anthropic.com/news/anthropic-raises-series-f-at-usd183b-post-money-valuation

Anthropic raises $13B Series F at $183B post-money valuation
Anthropic has completed a Series F fundraising of $13 billion led by ICONIQ. This financing values Anthropic at $183 billion post-money. Along with ICONIQ, the round was co-led by Fidelity Management & Research Company and Lightspeed Venture Partners. The investment reflects Anthropic’s continued momentum and reinforces our position as the leading intelligence platform for enterprises, developers, and power users.

Deep Reinforcement Learning for Ranking Utility Tuning in the Ad Recommender System at Pinterest
Xiao Yang, Mehdi Ben Ayed, Longyu Zhao, Fan Zhou, Yuchen Shen, Abe Engle, Jinfeng Zhuang, Ling Leng, Jiajing Xu, Charles Rosenberg, Prathibha Deshikachar
https://arxiv.org/abs/2509.05292

Deep Reinforcement Learning for Ranking Utility Tuning in the Ad Recommender System at Pinterest
The ranking utility function in an ad recommender system, which linearly combines predictions of various business goals, plays a central role in balancing values across the platform, advertisers, and users. Traditional manual tuning, while offering simplicity and interpretability, often yields suboptimal results due to its unprincipled tuning objectives, the vast amount of parameter combinations, and its lack of personalization and adaptability to seasonality. In this work, we propose a general…

Cognitive Effort in the Two-Step Task: An Active Inference Drift-Diffusion Model Approach
Alvaro Garrido Perez, Viktor Lemoine, Amrapali Pednekar, Yara Khaluf, Pieter Simoens
https://arxiv.org/abs/2508.04435

Cognitive Effort in the Two-Step Task: An Active Inference Drift-Diffusion Model Approach
High-level theories rooted in the Bayesian Brain Hypothesis often frame cognitive effort as the cost of resolving the conflict between habits and optimal policies. In parallel, evidence accumulator models (EAMs) provide a mechanistic account of how effort arises from competition between the subjective values of available options. Although EAMs have been combined with frameworks like Reinforcement Learning to bridge the gap between high-level theories and process-level mechanisms, relatively les…

Interacting vertex reinforced random walks on complete sub-graphs
Fernando P. A. Prado, Rafael A. Rosales
https://arxiv.org/abs/2508.15992 https://arxiv.or…

Interacting vertex reinforced random walks on complete sub-graphs
This article introduces a model for interacting vertex-reinforced random walks, each taking values on a complete sub-graph of a locally finite undirected graph. The transition probability for a walk to a given vertex depends on the cumulative proportion of visits by all walks that have access to that vertex. Proportions are modified by multiplication by a real valued interaction parameter and the addition of a parameter representing the intrinsic preference of the walk for the vertex. This mode…

On the Convergence of Policy Mirror Descent with Temporal Difference Evaluation
Jiacai Liu, Wenye Li, Ke Wei
https://arxiv.org/abs/2509.18822 https://arxiv…

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
Yiran Shen, Yu Xia, Jonathan Chang, Prithviraj Ammanabrolu
https://arxiv.org/abs/2510.01167 h…

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single optimizeable objective. We seek to answer what it would take to simultaneously align a model across various domains spanning those with: verifiable rewards (mathematical accuracy), non-verifiable subjective preferences (human values), and complex interactive scenarios (multi-turn AI tutoring dialogues). Such multi-objective reinforcement learning se…