arXiv Machine Learning
Aug 4
Humans Are More Diverse: Frontier LLMs Show Extreme Policies in Idealised AI Development Races
arXiv:2608. 01193v1 Announce Type: cross Abstract: An AI development race creates a multi-agent safety dilemma.
AI agents
Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv Machine Learning
Aug 4
RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States
arXiv:2608. 02508v1 Announce Type: new Abstract: Learning-based memory systems for self-evolving LLM agents face two tightly coupled challenges.
arXiv Machine Learning
Aug 4
Progressive Agent Skill Generation via Reinforcement Learning
arXiv:2608. 01678v1 Announce Type: new Abstract: Existing skill generation methods largely rely on heuristics or pipeline-style consolidation, which must be specially designed for different evidence sources.
arXiv Machine Learning
Aug 4
Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training
arXiv:2608. 02391v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents produce long, multi-turn trajectories, making gradient-based post-training memory-intensive.
arXiv Machine Learning
Aug 4
Native Multilingual Chain-of-Thought Reasoning in Low-Resource Southeast Asian Languages
arXiv:2608. 00533v1 Announce Type: cross Abstract: Large Language Models have achieved substantial progress in reasoning capabilities.
arXiv Machine Learning
Aug 4
From Vessel Trajectories to Safety-Critical Encounter Scenarios: A Generative AI Framework for Autonomous Ship Digital Testing
arXiv:2603. 28067v2 Announce Type: replace Abstract: Digital testing has emerged as a key paradigm for the development and verification of autonomous maritime navigation systems, yet the availability of realistic and diverse safety-critical encounter scenarios remains limited.
arXiv Machine Learning
Aug 4
Who Belongs in the Eval Set? A Capability-Taxonomy-Driven Pipeline for Curating Regression Eval Sets in Agent-Extensibility Platforms
arXiv:2608. 01004v1 Announce Type: new Abstract: Platform teams hosting agent-extensibility surfaces face a regression-economics paradox: every onboarding customer ships an evaluation set tuned to their domain, but the platform's regression set must live under a hard query-count ceiling bounded by release cadence.
arXiv Machine Learning
Aug 4
Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamics
arXiv:2602. 11439v3 Announce Type: replace Abstract: Strategic classification studies the problem where self-interested individuals or agents manipulate their response to obtain favorable decision outcomes made by classifiers, typically turning to dishonest actions when they are less costly than genuine efforts.
arXiv Machine Learning
Aug 4
A False Average: Chain-of-Thought Monitors Collapse Where They Are the Only Defense
arXiv:2608. 00583v1 Announce Type: cross Abstract: Chain-of-thought (CoT) monitoring is meant to catch the reward hacks that look clean in the actions and betray themselves only in the reasoning.
arXiv Machine Learning
Aug 4
Domain-Generalized Adaptive Semantic Communication for Collaborative Perception
arXiv:2608. 00056v1 Announce Type: cross Abstract: We propose RSTA, a domain-generalized semantic communication framework enabling source-free V2X collaborative perception under both observation-domain shift and unseen wireless channel conditions.
arXiv Machine Learning
Aug 4
When Replanning Becomes the Bottleneck: Budgeted Replanning for Embodied Agents
arXiv:2608. 01428v1 Announce Type: cross Abstract: Embodied agents replan frequently to recover from execution drift, partial observability, and coordination hazards, but each LLM-based replanning call can consume an accumulated textual context that grows over time and across agents.
arXiv Machine Learning
Aug 4
Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production Scale
arXiv:2608. 00101v1 Announce Type: cross Abstract: AI coding agents like GitHub Copilot, Claude Code, and Codex interleave multi-step LLM inference with tool execution, creating a workload different from chatbots.
arXiv Machine Learning
Aug 4
RMSWeb: Reflection, Failure-Mode Mining, and Salvage-DS for Web Agent Reinforcement Learning
arXiv:2608. 00335v1 Announce Type: cross Abstract: Compact web agents can reduce deployment cost, but training them poses challenges in both data collection and post-SFT reinforcement learning (RL).
arXiv Machine Learning
Aug 4
Belief-Contraction-Driven Active Inverse Source Localization and Characterization
arXiv:2501. 13084v2 Announce Type: replace Abstract: Active inverse source localization and characterization (ISLC) in dynamic fields requires sequential decision making under partial observability, where a mobile sensor must infer latent source parameters from sparse, noisy readings.
arXiv Machine Learning
Aug 4
Beckmann Transport Models: From Autonomous Flows to One-Step Maps
arXiv:2608. 01692v1 Announce Type: new Abstract: We propose an instantiation of flow matching that relies on a time-independent velocity field (an \emph{autonomous flow}) to exactly map between two distributions, so long as the target is singular, i.
arXiv Machine Learning
Aug 4
NashPG: A Policy Gradient Method with Iteratively Refined Regularization for Finding Nash Equilibria
arXiv:2510. 18183v3 Announce Type: replace Abstract: Finding Nash equilibria in two-player zero-sum imperfect-information games remains a central challenge in multi-agent reinforcement learning.
arXiv Machine Learning
Aug 4
Scoring Rules! Statistical and Strategic Alignment for Text Evaluation Metrics
arXiv:2608. 01423v1 Announce Type: cross Abstract: Reference-based text evaluation metrics, which are widely used to assess natural language generation systems, score a candidate response by comparing it with a reference response.
arXiv Machine Learning
Aug 4
Adaptive Reconstruction of Bosonic Quantum States
arXiv:2608. 02049v1 Announce Type: cross Abstract: Bosonic quantum systems provide a hardware-efficient platform for quantum information processing but remain challenging to characterise due to their large Hilbert space and the high measurement cost of state tomography.
arXiv Machine Learning
Aug 4
Why Formal Monitors Fail: Attack Distribution Entropy as a Coverage Bound for LTL-Based LLM Agent Safety
arXiv:2608. 01388v1 Announce Type: cross Abstract: Runtime safety monitors based on Linear Temporal Logic (LTL) and finite automata (FSA) are increasingly deployed to intercept unsafe tool-call sequences in LLM agents.
arXiv Machine Learning
Aug 4
Neural operator learning for collision-aware trajectory planning of spacecraft swarms
arXiv:2608. 00320v1 Announce Type: new Abstract: Autonomous spacecraft swarms must plan fuel-efficient, collision-free maneuvers in increasingly congested orbits, yet classical trajectory optimization scales poorly as pairwise safety constraints multiply with swarm size, and learning-based planners rarely transfer across swarm sizes or debris densities.