Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2605.29268v3 Announce Type: replace-cross Abstract: LLM-guided evolutionary search (Evolve systems) has reached state-of-the-art results on mathematical and combinatorial tasks, yet most existi...
arXiv:2609.07534v2 Announce Type: replace-cross Abstract: Contact-rich assembly remains challenging because it requires submillimeter spatial accuracy and reliable interpretation of forces during sus...
arXiv:2408.09838v3 Announce Type: replace Abstract: A continual learning agent builds on previous experiences to develop increasingly complex behaviors by adapting to non-stationary and dynamic envir...
arXiv:2609. 13954v1 Announce Type: new Abstract: Ensemble sampling offers a practical approach to randomized exploration by maintaining a collection of models, but how small an ensemble can be while retaining strong regret guarantees remains unresolved.
CHAI for LLMs is a framework that improves large language models’ performance on code‑mixed translation tasks by using LLMs as annotators to create preference data, applying reinforcement learning from AI feedback, incorporating LLM‑generated domain knowledge for iterative refinement, and evaluating on real‑world datasets. The approach yields a 68.45% average win rate over state‑of‑the‑art open‑source models in human‑adjudicated tests. It demonstrates a scalable method to enhance code‑mixed language understanding in open‑source LLMs.
The paper investigates continuous‑time stochastic control problems with unknown drift and running reward functions, using an exploratory reinforcement learning framework that incorporates relaxed controls and entropy regularization. It develops policy‑iteration algorithms based on probabilistic representations of the optimal value function and its gradient, proving convergence and demonstrating performance through numerical examples. The study also extends to a special case with control‑dependent diffusion, requiring a Hessian representation.
The paper introduces TTIQ, a test‑time reinforcement learning framework that improves vision‑language model (VLM) adaptation by explicitly measuring image‑question dependence. By teacher‑forcing responses on the original and ablated image‑question pairs, TTIQ derives token‑level likelihood changes to estimate how much each input contributes, then uses these signals to construct a reward that favors jointly grounded, confident responses. Experiments on eight VQA datasets and various VLM sizes show that TTIQ consistently outperforms prior consensus‑based methods and generalizes across model families and unseen datasets.
arXiv:2609.14066v1 Announce Type: cross Abstract: Although existing multi-agent Retrieval-Augmented Generation (RAG) systems have demonstrated promise on complex multimodal reasoning tasks, they rema...
arXiv:2609.14261v1 Announce Type: cross Abstract: Recent robot learning paradigms increasingly rely on large offline datasets of robotic interactions to train control policies. Expressive generative...
arXiv:2609.15297v1 Announce Type: new Abstract: In order to make Reinforcement Learning algorithms applicable in real world scenarios, safety must be ensured even under adverse operating conditions....
arXiv:2609.13457v1 Announce Type: new Abstract: Timeseries multimodal large language models (TS-MLLMs) have recently begun leveraging the reasoning capabilities of large language models (LLMs) for qu...
arXiv:2609.14567v1 Announce Type: cross Abstract: Reinforcement learning (RL) has shown considerable promise for robotic decision-making, yet deploying multi-agent RL (MARL) on physical multi-robot s...
arXiv:2609.13916v1 Announce Type: new Abstract: We present North Small Translate, an open-weight, LLM-based machine translation (MT) model with instruction-following capabilities built on the same fo...
arXiv:2609.12394v2 Announce Type: replace Abstract: Mobile GUI agents are shifting from multi-module frameworks to native models trained end-to-end, yet industrial deployment faces three persistent g...
arXiv:2609.14648v1 Announce Type: new Abstract: Aligning multi-turn dialogue agents is usually framed as matching turn-level human preferences, yet direct optimization of long-term outcomes is often...
CodeTS introduces a verifiable framework for generating time series from natural language by translating textual temporal descriptions into executable code, which then produces the desired series. The approach constructs aligned Text‑Code‑TS triplets for supervised initialization and employs multi‑stage execution‑based rewards to ensure code validity and time‑series quality. Experiments on eight benchmarks show that CodeTS outperforms both LLM‑based and supervised generative baselines, offering a strong zero‑shot solution for Text‑to‑TS generation.
arXiv:2609.15169v1 Announce Type: new Abstract: Driving vision-language-action (VLA) models increasingly reason before acting, but their intermediate reasoning is often weakly grounded in physical sc...
The study presents a virtual imaging trial framework that uses reinforcement learning to optimize computed tomography (CT) protocols, balancing liver lesion detectability against radiation dose. By training a Proximal Policy Optimization agent on 63 computational human models across 468 parameter combinations, the authors demonstrate that evaluating only eight protocols per patient—about 2% of exhaustive testing—recovers 98.2% of the optimal objective. Conditioning the agent on patient‑specific CT localizer embeddings further improves zero‑simulation recovery by 10.7 percentage points compared to a localizer‑blind policy.
arXiv:2609.15361v1 Announce Type: cross Abstract: Effective communication is a cornerstone of distributed intelligence in Multi-Agent Reinforcement Learning (MARL), yet ensuring that generated messag...
arXiv:2609.14952v1 Announce Type: new Abstract: Dynamic cloud workflow scheduling must balance deadline satisfaction, container utilization, and energy consumption while dealing with stochastic task-...