LLMscape is an interactive installation that investigates how humans and AI construct meaning under shared conditions of uncertainty. Within a mutable, projection-mapped landscape, human participants reshape the world and engage with multiple AI agents, each developing incomplete and provisional accounts of their environment. Exhibited in Shanghai and continually evolving, the work positions AI not as deterministic tools but as embodied co-witnesses to an unstable world, examining the parallels between human and artificial meaning-making and inviting reflection on our shared epistemic limits.

RAG (Retrieval-Augmented Generation) systems and web agents are increasingly evaluated on multi-hop deep search tasks, yet current practice suffers from two major limitations. First, most benchmarks leak the reasoning path in the question text, allowing models to follow surface cues rather than discover reasoning chains autonomously. Second, evaluation is typically reduced to a single pass rate, which collapses diverse behaviours into one score and obscures whether failures stem from inadequate search, poor knowledge use, or inappropriate refusal. To address these issues, we present WebDetective, a benchmark of hint-free multi-hop questions paired with a controlled Wikipedia sandbox that ensures full traceability of model actions, and a holistic evaluation framework that separates search sufficiency, knowledge utilisation, and refusal behaviour. Our evaluation of 25 state-of-the-art models reveals systematic weaknesses across all architectures: models struggle with knowledge utilisation despite having sufficient evidence and demonstrate near-absent appropriate refusal when evidence is lacking. These patterns expose a fundamental gap: today's systems excel at executing given reasoning paths but fail when required to discover them. We develop an agentic workflow, EvidenceLoop, that explicitly targets the challenges our benchmark identifies, incorporating verification loops and systematic evidence tracking that improve both search and synthesis capabilities. This baseline demonstrates that WebDetective's diagnostic framework can guide concrete architectural improvements, establishing our benchmark as a critical tool for developing genuinely autonomous reasoning systems rather than pattern-following agents.

Multi-agent trajectory prediction in autonomous driving requires a comprehensive understanding of complex social dynamics. Existing methods, however, often struggle to capture the full richness of these dynamics, particularly the co-existence of multi-scale interactions and the diverse behaviors of heterogeneous agents. To address these challenges, this paper introduces HeLoFusion, an efficient and scalable encoder for modeling heterogeneous and multi-scale agent interactions. Instead of relying on global context, HeLoFusion constructs local, multi-scale graphs centered on each agent, allowing it to effectively model both direct pairwise dependencies and complex group-wise interactions (\textit{e.g.}, platooning vehicles or pedestrian crowds). Furthermore, HeLoFusion tackles the critical challenge of agent heterogeneity through an aggregation-decomposition message-passing scheme and type-specific feature networks, enabling it to learn nuanced, type-dependent interaction patterns. This locality-focused approach enables a principled representation of multi-level social context, yielding powerful and expressive agent embeddings. On the challenging Waymo Open Motion Dataset, HeLoFusion achieves state-of-the-art performance, setting new benchmarks for key metrics including Soft mAP and minADE. Our work demonstrates that a locality-grounded architecture, which explicitly models multi-scale and heterogeneous interactions, is a highly effective strategy for advancing motion forecasting.

HE development of autonomous vehicles (A Vs) is on the verge of passing beyond the laboratory and simulation tests and is shifting towards addressing the challenges that limit their practicality in today's society. While there is still need for further technological improvements to enable safe and smooth operation of a single A V, a great deal of research attention is being focused on the emerging challenge of operating multiple A Vs and the co-existence of A Vs and human-driven vehicles (HVs) [1], [2]. A realistic outlook for the adoption of autonomous vehicles on the roads is a mixed-traffic scenario in which human drivers with different driving styles and social preferences share the road with A Vs that are perhaps built by different manufacturers and hence follow different policies [3], [4]. In this work, we seek a solution that can ensure the safety and robustness of A Vs in the presence of human drivers with heterogeneous behavioral traits. Connected & autonomous vehicles (CA Vs) via vehicle-to-vehicle (V2V) communication allow vehicles to directly communicate with their neighbors, creating an extended perception that enables explicit coordination among vehicles to overcome the limitations of an isolated agent [5]-[11]. While planning in a fully A V scenario is relatively easy to achieve, coordination in the presence of HVs is a significantly more challenging task, as the A Vs not only need to react to road objects but also need to consider the behaviors of HVs [3], [4], [12]. We start by identifying the major challenges in the domain of behavior planning and prediction for A Vs in mixed-autonomy traffic.

With the adoption of autonomous vehicles on our roads, we will witness a mixed-autonomy environment where autonomous and human-driven vehicles must learn to coexist by sharing the same road infrastructure. T o attain socially-desirable behaviors, autonomous vehicles must be instructed to consider the utility of other vehicles around them in their decision-making process. Particularly, we study the maneuver planning problem for autonomous vehicles and investigate how a decentralized reward structure can induce altruism in their behavior and incentivize them to account for the interest of other autonomous and human-driven vehicles. This is a challenging problem due to the ambiguity of a human driver's willingness to cooperate with an autonomous vehicle. Thus, in contrast with the existing works which rely on behavior models of human drivers, we take an end-to-end approach and let the autonomous agents to implicitly learn the decision-making process of human drivers only from experience. W e introduce a multi-agent variant of the synchronous Advantage Actor-Critic (A2C) algorithm and train agents that coordinate with each other and can affect the behavior of human drivers to improve traffic flow and safety.Accepted to 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021) W orkshop on Autonomous Driving: Perception, Prediction and Planning

Australia's vast savannas are changing, and AI is showing us how Australia has the largest intact savannas on Earth . Savannas are an ever-changing mosaic of ecosystems - from the sparse grasslands to dense woodlands, forests and wetlands. They stretch from Cape York Peninsula in Queensland to the Kimberley in Western Australia, making up almost 25 per cent of Australia's landmass . Anticipating how savannas will change in the years ahead is crucial to help inform our decisions about land management and policy that reflect the region's cultural, environmental and economic values. To do this, our team created an artificial intelligence (AI) tool we've called Themeda, a name inspired by Themeda triandra, an iconic Australian native species known as'kangaroo grass' (as well as an acronym for Thematic Mapping of Ecosystem Dynamics).

A large amount of work has been done in Multi-Agent Systems (MAS) for modeling and solving problems with multiple interacting agents. However, most LLMs are pretrained independently and not specifically optimized for coordination. For example, existing LLM fine-tuning frameworks rely on individual rewards, which require complex reward designs for each agent to encourage collaboration. To address this challenge, we model LLM collaboration as a cooperative Multi-Agent Reinforcement Learning (MARL) problem. We develop a multi-agent, multi-turn algorithm, Multi-Agent Group Relative Policy Optimization (MAGRPO), to solve it, building on current RL approaches for LLMs as well as MARL techniques. Our experiments on LLM writing and coding collaboration demonstrate that fine-tuning multiple LLMs with MAGRPO enables agents to generate high-quality responses efficiently through effective cooperation. Our approach opens the door to using MARL methods for LLM collaboration and highlights the associated challenges.

Multi-agent systems of large language models (LLMs) show promise for complex reasoning, but their effectiveness is often limited by fixed collaboration protocols. These frameworks typically focus on macro-level orchestration while overlooking agents' internal deliberative capabilities. This critical meta-cognitive blindspot treats agents as passive executors unable to adapt their strategy based on internal cognitive states like uncertainty or confidence. We introduce the Meta-Policy Deliberation Framework (MPDF), where agents learn a decentralized policy over a set of high-level meta-cognitive actions: Persist, Refine, and Concede. To overcome the instability of traditional policy gradients in this setting, we develop SoftRankPO, a novel reinforcement learning algorithm. SoftRankPO stabilizes training by shaping advantages based on the rank of rewards mapped through smooth normal quantiles, making the learning process robust to reward variance. Experiments show that MPDF with SoftRankPO achieves a a 4-5% absolute gain in average accuracy across five mathematical and general reasoning benchmarks compared to six state-of-the-art heuristic and learning-based multi-agent reasoning algorithms. Our work presents a paradigm for learning adaptive, meta-cognitive policies for multi-agent LLM systems, shifting the focus from designing fixed protocols to learning dynamic, deliberative strategies.

Multi-Agent Reinforcement Learning (MARL) is commonly deployed in settings where agents are trained via self-play with homogeneous teammates, often using parameter sharing and a single policy architecture. This opens the question: to what extent do self-play PPO agents learn general coordination strategies grounded in the underlying game, compared to overfitting to their training partners' behaviors? This paper investigates the question using the Heterogeneous Multi-Agent Challenge (HeMAC) environment, which features distinct Observer and Drone agents with complementary capabilities. We introduce Rotating Policy Training (RPT), an approach that rotates heterogeneous teammate policies of different learning algorithms during training, to expose the agent to a broader range of partner strategies. When playing alongside a withheld teammate policy (DDQN), we find that RPT achieves similar performance to a standard self-play baseline, IPPO, where all agents were trained sharing a single PPO policy. This result indicates that in this heterogeneous multi-agent setting, the IPPO baseline generalizes to novel teammate algorithms despite not experiencing teammate diversity during training. This shows that a simple IPPO baseline may possess the level of generalization to novel teammates that a diverse training regimen was designed to achieve.

Multi-robot systems performing continuous tasks face a performance trade-off when interrupted by urgent, time-critical sub-tasks. We investigate this trade-off in a scenario where a team must balance area patrolling with locating an anomalous radio signal. To address this trade-off, we evaluate both behavioral heterogeneity through agent role specialization ("patrollers" and "searchers") and sensing heterogeneity (i.e., only the searchers can sense the radio signal). Through simulation, we identify the Pareto-optimal trade-offs under varying team compositions, with behaviorally heterogeneous teams demonstrating the most balanced trade-offs in the majority of cases. When sensing capability is restricted, heterogeneous teams with half of the sensing-capable agents perform comparably to homogeneous teams, providing cost-saving rationale for restricting sensor payload deployment. Our findings demonstrate that pre-deployment role and sensing specialization are powerful design considerations for multi-robot systems facing time-conflicting tasks, where varying the degree of behavioral heterogeneity can tune system performance toward either task.