This work presents InfoAgent, a training-free framework for evidence-bound visual-symbolic program synthesis, which records factual payloads, evidence provenance, execution routes, and verification obligations in a typed dependency graph and introduces InfoGraphicBench-Evidence, where complete-checklist pass rates on 2...
Training and evaluating interactive language agents typically requires rich user interactions, yet collecting human feedback is expensive and difficult to scale. Simulated users offer a scalable alternative, but they must both resemble real user behavior and provide useful learning experiences for agents. In contrast,...
Hoang Phan, Dat Huynh, A. Zhmoginov et al.· 0 citations
Long-horizon reasoning improves complex question answering but often requires expensive chain-of-thought generation and may transfer shortcut-sensitive fragments during distillation. This paper addresses the focused problem of learning a compact student model that preserves decision-relevant logic while reducing shortc...
Jiang-Bo Feng, Jin-Chao Guo, Yu-Xiang He et al.· International journal of pat...· 0 citations
An emerging hypothesis about reinforcement learning (RL) post-training of large language models (LLMs) is that it merely sharpens existing behaviors of a base model, improving single-shot accuracy at the cost of solution coverage. Although this trade-off has been observed in math and coding tasks, it need not extend to...
Deep Perturbation Learning is evaluated in three roles in which prior work has positioned it for machine unlearning: a direct deletion signal (the strongest claim), a utility-preserving regularizer, and a warm start for adversarial unlearning.
Chen Wu, Chrispine Kambimbi, Qi Zeng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.