Predict Before You Modify: Learning Improvement Dynamics for Self-Evolving Agents
[Submitted on 26 Sep 2026] View PDF HTML (experimental) Abstract:Self-evolving agents improve through repeated cycles of modification and evaluation. However,…
Tag: cs.AI
SemTree: Judge-Aware Semantic Decision Trees for Inspectable and Repairable Rule Decisions
[Submitted on 27 Sep 2026] View PDF HTML (experimental) Abstract:Rule decisions such as content moderation, advertising compliance, and eligibility checks…
Physics-Informed State Space Models for Day-Ahead Photovoltaic Power Forecasting
[Submitted on 29 Sep 2026] View PDF HTML (experimental) Abstract:Accurate day-ahead photovoltaic (PV) power forecasting requires both strong temporal modeling…
Activation Steering with Jungian Cognitive Functions
[Submitted on 23 Jul 2026 (v1), last revised 13 Oct 2026 (this version, v3)] View PDF HTML (experimental) Abstract:Controlling combinations…
CMP: Robust Whole-Body Tracking for Loco-Manipulation via Competence Manifold Projection
[Submitted on 8 Apr 2026 (v1), last revised 12 Oct 2026 (this version, v2)] View PDF HTML (experimental) Abstract:While decoupled…
Scale, Drivers, and Limits of Representational Alignment Across Large Language Models
[Submitted on 10 Oct 2026] View PDF HTML (experimental) Abstract:Comparing large language models can reveal shared representational structure and systematic…
inLoRA-MINT: Internal Representations for Auditing Training Data in Domain-adapted LLMs
[Submitted on 13 Oct 2026] View PDF HTML (experimental) Abstract:This work investigates the application of the Membership Inference Test (MINT)…
VH-GPO: Verified Handoff for LLM Agent Reinforcement Learning
[Submitted on 27 Sep 2026] View PDF HTML (experimental) Abstract:Group-relative reinforcement learning methods such as GRPO train large language model…
Identification of Entailment and Contradiction Relations for Natural Language Argumentation: A Neurosymbolic Approach
[Submitted on 2 May 2024 (v1), last revised 12 Oct 2026 (this version, v2)] View PDF HTML (experimental) Abstract:Argumentation is…
ChunkAct: Action Chunking for Agentic Robotics
[Submitted on 13 Oct 2026] View PDF HTML (experimental) Abstract:Agentic robotics places a large language model (LLM) agent in the…