arXiv AI
4d ago
Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents
arXiv:2608. 14339v1 Announce Type: new Abstract: We study proactive exploration in LLM agents, i.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
4d ago
Measuring Cross-Task Behavioral Consistency in Language Model Agents
arXiv:2608. 13598v1 Announce Type: new Abstract: Agent evaluation relies almost entirely on outcome metrics such as success rate, which capture whether an agent succeeds but not how consistently it behaves.
arXiv Machine Learning
4d ago
MINT: A Universal Zero-Shot Predictor for Transaction Data
arXiv:2608. 14198v1 Announce Type: new Abstract: Banks analyse sequential financial transaction data to perform many tasks, including fraud prevention, credit risk assessment and offer personalization.
arXiv Machine Learning
4d ago
Detecting Contaminated Code-Generation Prompt Batches via Influence Functions
arXiv:2608. 14303v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for code generation, yet they remain vulnerable to prompts that elicit insecure implementations.
arXiv AI
4d ago
Active Perception for Embodied Disambiguation
arXiv:2608. 13605v1 Announce Type: new Abstract: Natural language provides robots with a flexible task interface, but target ambiguity in embodied environments arises not only from user intent; it can also result from missing taskrelevant physical evidence in the current observation.
arXiv Machine Learning
4d ago
KV Cache Compression Through the Lens of Transform Coding
arXiv:2608. 14191v1 Announce Type: new Abstract: The key-value (KV) cache stores information from past tokens and is a major memory bottleneck in long-context inference.
arXiv AI
4d ago
Fine-Tuning Qwen3-27B for C-to-Rust Code Translation: A Three-Stage Curriculum of Pretraining, Debugging-Aware SFT, and Task-Specific SFT
arXiv:2608. 13681v1 Announce Type: cross Abstract: Translating C code into safe, idiomatic Rust is a longstanding software-engineering goal because it can eliminate entire classes of memory-safety vulnerabilities while preserving the functional behavior of legacy systems.
arXiv AI
4d ago
Whose doctor does the AI recommend? An algorithm audit of reputation and demographic signals in large language model-assisted physician choice
arXiv:2608. 14399v1 Announce Type: cross Abstract: Patients increasingly ask large language model (LLM) assistants which doctor to see, making these systems AI infomediaries: algorithms that intermediate one person's choice among other people and thereby decide, silently and at scale, which physicians become visible.
arXiv AI
4d ago
INFORM-CT: INtegrating LLMs and VLMs FOR Incidental Findings Management in Abdominal CT
arXiv:2512. 14732v3 Announce Type: replace-cross Abstract: Incidental findings in CT scans, though often benign, can have significant clinical implications and should be reported following established guidelines.
arXiv AI
4d ago
The Fools are Certain; the Wise are Doubtful: Exploring LLM Confidence in Code Completion
arXiv:2508. 16131v3 Announce Type: replace-cross Abstract: Code completion entails the task of providing missing tokens given a surrounding context.
arXiv AI
4d ago
Cloud-ScPO: Hidden-State Geometry for Semi-Supervised Preference Optimization in LLM Reasoning
arXiv:2608. 01014v2 Announce Type: replace-cross Abstract: Preference optimization improves mathematical reasoning in large language models (LLMs), but reliable chosen-rejected pairs usually require verified answers, human annotations, or external reward models.
arXiv Machine Learning
4d ago
Localization then Neutralization: Gradient-guided Token Suppression against Visual Prompt Injection Attack
arXiv:2605. 25194v2 Announce Type: replace Abstract: Adversarial images pose a severe security threat to multimodal large language models through prompt injection.
arXiv Machine Learning
4d ago
Language-Specific Gaps in AI Safety Training Datasets
arXiv:2608. 13695v1 Announce Type: cross Abstract: Large language model providers routinely cite multilingual safety benchmarks spanning a dozen or more languages as evidence that their models are safe for non-English-speaking users.
arXiv AI
4d ago
Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency
arXiv:2608. 14065v1 Announce Type: cross Abstract: Background: Software bugs remain a critical challenge in development, necessitating effective Automated Program Repair (APR) techniques.
arXiv Machine Learning
4d ago
Non-Parametric Spatiotemporal Trajectory Prediction via State-Conditioned Transition Sampling
arXiv:2608. 14349v1 Announce Type: new Abstract: We present a training-free method for multi-modal trajectory prediction that achieves comparable accuracy to a 57M-parameter transformer while requiring no GPU and zero learned parameters.
arXiv AI
4d ago
ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond
arXiv:2608. 14354v1 Announce Type: new Abstract: Enabling LLM agents to sustain productive, stable, and goal-aligned research over extended horizons is a central challenge for autonomous machine learning and scientific discovery, as progress hinges on continuously managing evolving state, exploration decisions, and computational resources.
arXiv AI
4d ago
Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation
arXiv:2608. 13564v1 Announce Type: new Abstract: Evaluating language-model agents at scale increasingly relies on a second language model as an automatic judge, because the gold signal, an executable environment reward, is expensive, slow, or unavailable at deployment time.
arXiv AI
4d ago
EchoChange: A Diffusion Language Model with Dual Pass Remasking for Factual Remote Sensing Disaster Change Captioning
arXiv:2608. 01856v2 Announce Type: replace Abstract: Bi-temporal remote-sensing disaster change captioning often needs to identify sparse and spatially localized changes across large pre- and post-event scenes and then translate them into coherent, factual descriptions.
arXiv AI
4d ago
SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning
arXiv:2608. 14277v1 Announce Type: cross Abstract: On-policy distillation (OPD) offers a promising way to transfer reasoning capabilities from stronger teacher models, but applying it to long-context reasoning teachers and short-context students introduces practical challenges, including tokenizer mismatch, teacher-student distribution mismatch, response length explosion, and training instability.
arXiv AI
4d ago
LLM-Advisor: An LLM Advisor for Cost-efficient Path Planning across Multiple Terrains
arXiv:2503. 01236v3 Announce Type: replace-cross Abstract: This paper addresses fixed-graph terrain-aware path refinement, in which a global planner is restricted to a predefined route space and may remain optimal within that space while missing lower-cost terrain corridors available in the native-resolution map.