Reward Prediction with Factorized World States
arXiv:2603.09400v1 Announce Type: new Abstract: Agents must infer action outcomes and select actions that maximize a reward signal indicating how close the goal is to being reached. Supervised learning of reward models could introduce biases inherent to training data, limiting...
SPAR-K: Scheduled Periodic Alternating Early Exit for Spoken Language Models
arXiv:2603.09215v1 Announce Type: new Abstract: Interleaved spoken language models (SLMs) alternately generate text and speech tokens, but decoding at full transformer depth for every step becomes costly, especially due to long speech sequences. We propose SPAR-K, a modality-aware early exit...
Let's Verify Math Questions Step by Step
arXiv:2505.13903v1 Announce Type: cross Abstract: Large Language Models (LLMs) have recently achieved remarkable progress in mathematical reasoning. To enable such capabilities, many existing works distill strong reasoning models into long chains of thought or design algorithms to construct high-quality math...
MedMASLab: A Unified Orchestration Framework for Benchmarking Multimodal Medical Multi-Agent Systems
arXiv:2603.09909v1 Announce Type: new Abstract: While Multi-Agent Systems (MAS) show potential for complex clinical decision support, the field remains hindered by architectural fragmentation and the lack of standardized multimodal integration. Current medical MAS research suffers from non-uniform data ingestion pipelines,...
An Empirical Study and Theoretical Explanation on Task-Level Model-Merging Collapse
arXiv:2603.09463v1 Announce Type: new Abstract: Model merging unifies independently fine-tuned LLMs from the same base, enabling reuse and integration of parallel development efforts without retraining. However, in practice we observe that merging does not always succeed: certain combinations of task-specialist...
Deep Tabular Research via Continual Experience-Driven Execution
arXiv:2603.09151v1 Announce Type: new Abstract: Large language models often struggle with complex long-horizon analytical tasks over unstructured tables, which typically feature hierarchical and bidirectional headers and non-canonical layouts. We formalize this challenge as Deep Tabular Research (DTR), requiring multi-step reasoning...
AutoAgent: Evolving Cognition and Elastic Memory Orchestration for Adaptive Agents
arXiv:2603.09716v1 Announce Type: new Abstract: Autonomous agent frameworks still struggle to reconcile long-term experiential learning with real-time, context-sensitive decision-making. In practice, this gap appears as static cognition, rigid workflow dependence, and inefficient context usage, which jointly limit adaptability in open-ended...
Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs
arXiv:2603.09095v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can process text presented as images, yet they often perform worse than when the same content is provided as textual tokens. We systematically diagnose this "modality gap" by evaluating seven...
Explainable Innovation Engine: Dual-Tree Agent-RAG with Methods-as-Nodes and Verifiable Write-Back
arXiv:2603.09192v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves factual grounding, yet most systems rely on flat chunk retrieval and provide limited control over multi-step synthesis. We propose an Explainable Innovation Engine that upgrades the knowledge unit from text chunks...
Context Engineering: From Prompts to Corporate Multi-Agent Architecture
arXiv:2603.09619v1 Announce Type: new Abstract: As artificial intelligence (AI) systems evolve from stateless chatbots to autonomous multi-step agents, prompt engineering (PE), the discipline of crafting individual queries, proves necessary but insufficient. This paper introduces context engineering (CE) as a standalone...
DataFactory: Collaborative Multi-Agent Framework for Advanced Table Question Answering
arXiv:2603.09152v1 Announce Type: new Abstract: Table Question Answering (TableQA) enables natural language interaction with structured tabular data. However, existing large language model (LLM) approaches face critical limitations: context length constraints that restrict data handling capabilities, hallucination issues that compromise answer...
Learning When to Sample: Confidence-Aware Self-Consistency for Efficient LLM Chain-of-Thought Reasoning
arXiv:2603.08999v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong reasoning performance through chain-of-thought (CoT) reasoning, yet often generate unnecessarily long reasoning paths that incur high inference cost. Recent self-consistency-based approaches further improve accuracy but require sampling and aggregating...
Common Sense vs. Morality: The Curious Case of Narrative Focus Bias in LLMs
arXiv:2603.09434v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed across diverse real-world applications and user communities. As such, it is crucial that these models remain both morally grounded and knowledge-aware. In this work, we uncover a critical...
PrivPRISM: Automatically Detecting Discrepancies Between Google Play Data Safety Declarations and Developer Privacy Policies
arXiv:2603.09214v1 Announce Type: new Abstract: End-users seldom read verbose privacy policies, leading app stores like Google Play to mandate simplified data safety declarations as a user-friendly alternative. However, these self-declared disclosures often contradict the full privacy policies, deceiving users about...
AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystem
arXiv:2603.08938v1 Announce Type: new Abstract: The rapid emergence of open-source, locally hosted intelligent agents marks a critical inflection point in human-computer interaction. Systems such as OpenClaw demonstrate that Large Language Model (LLM)-based agents can autonomously operate local computing environments, orchestrate...
LDP: An Identity-Aware Protocol for Multi-Agent LLM Systems
arXiv:2603.08852v1 Announce Type: new Abstract: As multi-agent AI systems grow in complexity, the protocols connecting them constrain their capabilities. Current protocols such as A2A and MCP do not expose model-level properties as first-class primitives, ignoring properties fundamental to effective delegation:...
LooComp: Leverage Leave-One-Out Strategy to Encoder-only Transformer for Efficient Query-aware Context Compression
arXiv:2603.09222v1 Announce Type: new Abstract: Efficient context compression is crucial for improving the accuracy and scalability of question answering. For the efficiency of Retrieval Augmented Generation, context should be delivered fast, compact, and precise to ensure clue sufficiency and budget-friendly...
LCA: Local Classifier Alignment for Continual Learning
arXiv:2603.09888v1 Announce Type: new Abstract: A fundamental requirement for intelligent systems is the ability to learn continuously under changing environments. However, models trained in this regime often suffer from catastrophic forgetting. Leveraging pre-trained models has recently emerged as a promising...
MASEval: Extending Multi-Agent Evaluation from Models to Systems
arXiv:2603.08835v1 Announce Type: new Abstract: The rapid adoption of LLM-based agentic systems has produced a rich ecosystem of frameworks (smolagents, LangGraph, AutoGen, CAMEL, LlamaIndex, i.a.). Yet existing benchmarks are model-centric: they fix the agentic setup and do not compare other...
Surgical Repair of Collapsed Attention Heads in ALiBi Transformers
arXiv:2603.09616v1 Announce Type: new Abstract: We identify a systematic attention collapse pathology in the BLOOM family of transformer language models, where ALiBi positional encoding causes 31-44% of attention heads to attend almost entirely to the beginning-of-sequence token. The collapse follows...
Understanding the Interplay between LLMs' Utilisation of Parametric and Contextual Knowledge: A keynote at ECIR 2025
arXiv:2603.09654v1 Announce Type: new Abstract: Language Models (LMs) acquire parametric knowledge from their training process, embedding it within their weights. The increasing scalability of LMs, however, poses significant challenges for understanding a model's inner workings and further for updating or...
One-Eval: An Agentic System for Automated and Traceable LLM Evaluation
arXiv:2603.09821v1 Announce Type: new Abstract: Reliable evaluation is essential for developing and deploying large language models, yet in practice it often requires substantial manual effort: practitioners must identify appropriate benchmarks, reproduce heterogeneous evaluation codebases, configure dataset schema mappings, and interpret...
Chow-Liu Ordering for Long-Context Reasoning in Chain-of-Agents
arXiv:2603.09835v1 Announce Type: new Abstract: Sequential multi-agent reasoning frameworks such as Chain-of-Agents (CoA) handle long-context queries by decomposing inputs into chunks and processing them sequentially using LLM-based worker agents that read from and update a bounded shared memory. From a...
N-gram-like Language Models Predict Reading Time Best
arXiv:2603.09872v1 Announce Type: new Abstract: Recent work has found that contemporary language models such as transformers can become so good at next-word prediction that the probabilities they calculate become worse for predicting reading time. In this paper, we propose that...
PathoScribe: Transforming Pathology Data into a Living Library with a Unified LLM-Driven Framework for Semantic Retrieval and Clinical Integration
arXiv:2603.08935v1 Announce Type: cross Abstract: Pathology underpins modern diagnosis and cancer care, yet its most valuable asset, the accumulated experience encoded in millions of narrative reports, remains largely inaccessible. Although institutions are rapidly digitizing pathology workflows, storing data without effective...
BiCLIP: Domain Canonicalization via Structured Geometric Transformation
arXiv:2603.08942v1 Announce Type: cross Abstract: Recent advances in vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities, yet adapting these models to specialized domains remains a significant challenge. Building on recent theoretical insights suggesting that independently trained VLMs are related by...
Equitable Multi-Task Learning for AI-RANs
arXiv:2603.08717v1 Announce Type: new Abstract: AI-enabled Radio Access Networks (AI-RANs) are expected to serve heterogeneous users with time-varying learning tasks over shared edge resources. Ensuring equitable inference performance across these users requires adaptive and fair learning mechanisms. This paper introduces...
SPREAD: Subspace Representation Distillation for Lifelong Imitation Learning
arXiv:2603.08763v1 Announce Type: new Abstract: A key challenge in lifelong imitation learning (LIL) is enabling agents to acquire new skills from expert demonstrations while retaining prior knowledge. This requires preserving the low-dimensional manifolds and geometric structures that underlie task representations...
Multi-level meta-reinforcement learning with skill-based curriculum
arXiv:2603.08773v1 Announce Type: new Abstract: We consider problems in sequential decision making with natural multi-level structure, where sub-tasks are assembled together to accomplish complex goals. Systematically inferring and leveraging hierarchical structure has remained a longstanding challenge; we describe an efficient...
The Temporal Markov Transition Field
arXiv:2603.08803v1 Announce Type: new Abstract: The Markov Transition Field (MTF), introduced by Wang and Oates (2015), encodes a time series as a two-dimensional image by mapping each pair of time steps to the transition probability between their quantile states, estimated...