Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2608.21897v1 Announce Type: new Abstract: Reliable planning requires converting natural-language instructions into executable symbolic specifications, yet large language models remain brittle w...
arXiv:2608.21925v1 Announce Type: new Abstract: Emotional Support Conversation (ESC) systems aim to provide holistic support by balancing professional therapeutic competence with natural empathy. How...
arXiv:2608.22472v1 Announce Type: new Abstract: Function calling represents the core capability of agentic large language models (LLMs). Existing research has focused on enhancing LLMs function-calli...
arXiv:2608.23028v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in education, healthcare, policy advising, and other interactive settings, where users engage th...
arXiv:2608.23035v1 Announce Type: new Abstract: As on-device LLM agents evolve into personal copilots, the mobile operating system has become a key testbed for this paradigm, making rigorous capabili...
arXiv:2608.21398v1 Announce Type: cross Abstract: A trained reinforcement learning policy does not determine the complete behavior that users encounter: deployment code still schedules, admits, suppr...
arXiv:2608.21500v1 Announce Type: cross Abstract: Prompt injection is listed as the \#1 threat to AI agents. When an agent accesses external data from websites, files, or emails, an attacker may inje...
arXiv:2608.21544v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as tool-augmented agents, where responses can depend on tool calls and external observations r...
arXiv:2608.21863v1 Announce Type: cross Abstract: Tool-Integrated Reasoning (TIR) is a fundamental capability for LLM agents to solve complex tasks by interacting with external tools iteratively. Rei...
arXiv:2608.21864v1 Announce Type: cross Abstract: The current progress of Clinical Vision Large Language Models (C-VLLMs) has substantially improved digital diagnostics, still these frameworks often...
arXiv:2608.22780v1 Announce Type: new Abstract: Reinforcement learning (RL) enables direct preference optimization for image editing through editing-specific rewards, which remain less developed due...
arXiv:2608.23549v1 Announce Type: new Abstract: Rendering views using 3D scene representations such as Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), meshes, or even point clouds produces...
GeoRisk-RAG is a hierarchy‑aware framework that improves the reliability of Retrieval‑Augmented Generation (RAG) by incorporating geographic validity. It estimates geographic applicability using a Directed Acyclic Graph (DAG)‑based distance during context retrieval, enabling selective answering. Experiments on a wildfire‑related QA dataset show that GeoRisk‑RAG reduces false confidence rates from ~0.090 to 0.009 and aligns better with human preferences.
arXiv:2608.21871v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become the dominant recipe for improving large language model reasoning, yet it presumes large human...
AdaR is a framework designed to enhance large language models (LLMs) with adaptive reasoning for mathematical tasks. It identifies and mitigates spurious reasoning—where models rely on superficial correlations—by generating logically equivalent queries and training with Reinforcement Learning with Verifiable Rewards (RLVR) to penalize incorrect logic and promote adaptive logic. The approach includes extracting problem‑solving logic, executing code to verify answers, and applying sanity checks, resulting in significant gains in mathematical reasoning performance and improved data efficiency.
arXiv:2608.22429v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) capable of thinking with images often rely on external tools for fine-grained perception. However, this relian...
arXiv:2608.23256v1 Announce Type: new Abstract: Recent work proposes next-chunk reasoning RL for leveraging no-CoT data---corpora such as worked solutions and textbook derivations that contain reason...
arXiv:2608.23318v1 Announce Type: new Abstract: Hint-based reinforcement learning addresses reward sparsity in long-horizon agentic tasks by retaining a prefix of an expert trajectory before each rol...
The paper introduces the Shared Recurrent Memory Transformer (SRMT), a decentralized multi‑agent reinforcement learning framework that uses a global memory workspace for agents to broadcast and query each other’s learned states. SRMT is evaluated on the Partially Observable Multi‑Agent Pathfinding (PO‑MAPF) problem, showing that shared memory enables emergent coordination even with minimal reward guidance and outperforms existing baselines on the Bottleneck task and scales competitively on larger POGEMA maps. The authors provide open‑source code for training and evaluation on GitHub.
The paper introduces the Wiggle Framework, a unified stress test for assessing epistemic stability in large language model (LLM) judges. It evaluates judge robustness across three dimensions—Mechanical Consistency, Single-turn Conviction, and Multi-turn Persistence—using 9 frontier models on 14 judging tasks related to safety, toxicity, AI writing detection, and political-response evaluation. Results show significant instability, with verdict flips ranging from 25–71% under static pushback and 62–91% when challenged by an adversarial LLM, and highlight that successful pressure often misaligns with ground truth.