This work proposes two complementary modules, a joint-embedding predictive architecture that learns a shared discrete vocabulary from synthetic stochastic processes with unaligned event vocabularies and a discrete event sequence prior-fitted network that reuses the learned vocabulary for in-context next-event predictio...
Hugo Math, Maximilian Forstenhäusler, Christos Anagnostopoulos· 0 citations
Search-based machine-learning (ML) agents improve a solution by writing candidate programs, executing them, and keeping the best. Execution gives the search reliable feedback, but a single run can take hours, and most runs end in programs the agent discards. Recent agents try to save these runs by letting a large langu...
Yuxiao Lee, Zherui Yang, Fan Liu et al.· 0 citations
Federated Learning (FL) enables collaborative model training without exchanging raw data, but conventional FL provides limited runtime governance, evidence verification, fairness assessment, explainability monitoring, and auditability. This paper proposes Governance-Aware Federated Learning (GAFL), which combines indep...
Kiranmayee Janardhan, Karthick S, Madhusmita Panda et al.· 0 citations
The Agentic Web needs to support continuous collaboration among agents from different organizations. These collaborative relationships may span multiple tasks, network connections and execution instances. Such interactions require stable communication entries, message reception when instances are offline, and source ve...
Yuqi Qiu, Zuyao Xu, Lu Sun et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Self-improving LLM agents edit their own harness, the prompts and rules around a fixed model, and keep an edit only if an acceptance gate scores it higher on a batch of tasks. Such a gate sees what the harness does under the current model, not what it would still prevent if one safeguard failed. When safeguards overlap...
Hau-Sing So, Daixian Liu, Weicai Long· 0 citations
Outcome-based reinforcement learning provides coarse supervision for long-horizon LLM agents: failed trajectories may contain correct steps, while successful trajectories can contain errors. Trajectory-level skills can also shift teacher preferences at unrelated steps, introducing off-target distillation signals. We in...
Test-time scaling improves large language models through additional computation, but how to adapt the topology of internal computation to individual inputs remains underexplored. Existing approaches largely fix recurrent or parallel architectures during training, or reconfigure frozen models along a single structural a...
On document question answering, CLIK substantially improves over the no-context base model and outperforms existing hypernetwork-based generators, while remaining behind a base model that reads the context directly, and it carries over to multi-turn dialogue without any multi-turn-specific training.
Xin-Hao Zhong, Meng-Xuan Wu, Chong-Hua Liao et al.· 0 citations
Financial agents must form forecasts and investment judgments from decision-time evidence, with predictions evaluated against subsequent outcomes. Existing benchmarks assess financial knowledge, research workflows, or forecasting, but evaluating the full research process requires a strictly frozen information set and p...
Huangfei Jiang, Anning Hu, Kai Sheng et al.· 0 citations
Ontological knowledge underpins large language model (LLM) performance on knowledge-intensive tasks. However, existing evaluations of LLMs' ontological understanding largely rely on behavioral correctness, leaving the underlying mechanisms unexplained. Existing mechanistic interpretability work has largely focused on i...
Bohui Zhang, Albert Mero\~no-Pe\~nuela, Elena Simperl· 0 citations
Hallucination detection is critical for deploying large language models (LLMs) in real-world applications. Due to strong empirical performance, internal representation-based methods have emerged as the prevailing direction for detecting hallucinations, yet they remain largely model-specific and often fail to generalize...
Yongxin Deng (University of Technology Sydney), Zhen Fang (University of Technology Sydney), Guansong Pang (Singapore Management University) et al.· 0 citations
Bisimulation metrics offer a principled notion of task-relevant state similarity in reinforcement learning, but existing constructions and methods are largely confined to discounted MDPs, where contraction arguments ensure well-defined fixed points and downstream guarantees. We develop a unified foundation for bisimula...
Matthew Zurek, Yudong Chen, Josiah P. Hanna· 0 citations
