arXiv:2603.20258v1 Announce Type: cross Abstract: Reliable detection of event-related potentials (ERPs) at the single-trial level remains a major challenge due to the low signal-to-noise ratio EEG recordings. In this work, we investigate whether incorporating prior knowledge about ERP templates into deep learning models can improve detection performance. We employ the Deep-Match framework for ERP detection […]
DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment
arXiv:2603.21461v1 Announce Type: cross Abstract: Preference alignment is usually achieved by weight-updating training on preference data, which adds substantial alignment-stage compute and provides limited mechanistic visibility. We propose Dynamic SAE Steering for Preference Alignment (DSPA), an inference-time method that makes sparse autoencoder (SAE) steering prompt-conditional. From preference triples, DSPA computes a conditional-difference map linking prompt […]
Effective Strategies for Asynchronous Software Engineering Agents
arXiv:2603.21489v1 Announce Type: cross Abstract: AI agents have become increasingly capable at isolated software engineering (SWE) tasks such as resolving issues on Github. Yet long-horizon tasks involving multiple interdependent subtasks still pose challenges both with respect to accuracy, and with respect to timely completion. A natural approach to solving these long-horizon tasks in a timely […]
Exploring Teacher-Chatbot Interaction and Affect in Block-Based Programming
arXiv:2603.20211v1 Announce Type: cross Abstract: AI-based chatbots have the potential to accelerate learning and teaching, but may also have counterproductive consequences without thoughtful design and scaffolding. To better understand teachers’ perspectives on large language model (LLM)-based chatbots, we conducted a study with 11 teams of middle school teachers using chatbots for a science and computational […]
Fusing Driver Perceived and Physical Risk for Safety Critical Scenario Screening in Autonomous Driving
arXiv:2603.20232v1 Announce Type: cross Abstract: Autonomous driving testing increasingly relies on mining safety critical scenarios from large scale naturalistic driving data, yet existing screening pipelines still depend on manual risk annotation and expensive frame by frame risk evaluation, resulting in low efficiency and weakly grounded risk quantification. To address this issue, we propose a driver […]
AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling
arXiv:2603.21357v1 Announce Type: new Abstract: LLM agents fail on the majority of real-world tasks — GPT-4o succeeds on fewer than 15% of WebArena navigation tasks and below 55% pass@1 on ToolBench (Zhou et al., 2024; Qin et al., 2024) — yet every failed trajectory is routinely discarded, wasting the dominant source of collected experience. We […]
DomAgent: Leveraging Knowledge Graphs and Case-Based Reasoning for Domain-Specific Code Generation
arXiv:2603.21430v1 Announce Type: new Abstract: Large language models (LLMs) have shown impressive capabilities in code generation. However, because most LLMs are trained on public domain corpora, directly applying them to real-world software development often yields low success rates, as these scenarios frequently require domain-specific knowledge. In particular, domain-specific tasks usually demand highly specialized solutions, which […]
Counterfactual Credit Policy Optimization for Multi-Agent Collaboration
arXiv:2603.21563v1 Announce Type: new Abstract: Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles and aggregating diverse hypotheses. Yet, reinforcement learning (RL) for such systems is often undermined by credit assignment: a shared global reward obscures individual contributions, inflating update variance and encouraging free-riding. We introduce Counterfactual Credit Policy Optimization […]
AI Token Futures Market: Commoditization of Compute and Derivatives Contract Design
arXiv:2603.21690v1 Announce Type: new Abstract: As large language models (LLMs) and vision-language-action models (VLAs) become widely deployed, the tokens consumed by AI inference are evolving into a new type of commodity. This paper systematically analyzes the commodity attributes of tokens, arguing for their transition from intelligent service outputs to compute infrastructure raw materials, and draws […]
The Reasoning Error About Reasoning: Why Different Types of Reasoning Require Different Representational Structures
arXiv:2603.21736v1 Announce Type: new Abstract: Different types of reasoning impose different structural demands on representational systems, yet no systematic account of these demands exists across psychology, AI, and philosophy of mind. I propose a framework identifying four structural properties of representational systems: operability, consistency, structural preservation, and compositionality. These properties are demanded to different degrees […]
GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning
arXiv:2603.22096v1 Announce Type: new Abstract: Clinical decision-making agents can benefit from reusing prior decision experience. However, many memory-augmented methods store experiences as independent records without explicit relational structure, which may introduce noisy retrieval, unreliable reuse, and in some cases even hurt performance compared to direct LLM inference. We propose GSEM (Graph-based Self-Evolving Memory), a clinical […]
Enhancing Safety of Large Language Models via Embedding Space Separation
arXiv:2603.20206v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved impressive capabilities, yet ensuring their safety against harmful prompts remains a critical challenge. Recent work has revealed that the latent representations (embeddings) of harmful and safe queries in LLMs typically exhibit linear separability, a property that has been exploited to construct attacks by perturbing […]