The Morning
From the arXiv
Auditable Long-Term Memory: A Deterministic Retrieval Chain Measured at 479/475 of 500 on LongMemEval-S
his paper introduces an auditable long-term memory system that achieves high performance on the LongMemEval-S benchmark. Its core method involves a deterministic retrieval chain combining hybrid candidate retrieval, cross-encoder reranking, and coverage-first packet compilation, with an LLM acting solely as a final reader. The system's main contribution is demonstrating strong, auditable long-term memory retrieval capabilities, scoring 479/500 and 475/500 on the benchmark, highlighting its potential for reliable knowledge recall.
Diagnosing and Improving Probabilistic Reasoning in Large Language Models
This paper proposes a decision-theoretic framework to analyze how Large Language Models (LLMs) make probabilistic decisions. It decomposes decision loss into belief accuracy and action optimization, using a synthetic benchmark to diagnose LLM reasoning. The st…
On Trajectory-Aware Training for Masked Diffusion Language Models
This paper introduces PUMBA, a unified framework for trajectory-aware training of masked diffusion language models. PUMBA addresses the mismatch between training and inference by training the model on consecutive steps of predicted trajectories and passing inf…
SelfSearch: Reward-Free Search for Self-Improving Agents
SelfSearch enables LLM agents to improve themselves without needing external rewards. It achieves this by using past self-improvement attempts, including reasoning and outcomes, as experience to guide future modifications. This reward-free approach leads to be…
The Unequal Influence of Bad Advice: Using Training Data Attribution to Modulate Emergent Misalignment
This paper investigates how fine-tuning large language models can lead to "emergent misalignment" by amplifying harmful personas. The core method uses training data attribution to quantify the influence of individual harmful examples on this misalignment. The …
Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning
This paper introduces "agentic meta-reasoning," a system where a controller makes explicit, structured decisions about how to proceed with a complex task. Instead of replaying the …
UserProxyBench: Evaluating LLM User Simulators for Agent Benchmarks and Training
This paper introduces UserProxyBench, a framework to evaluate the performance of LLM-based user simulators in agent benchmarks. It proposes the User Fidelity Score (UFS) to measure…
TabFM-Auto: Self-Evolving Pipelines for Tabular Foundation Models
TabFM-Auto addresses limitations of existing tabular foundation models and self-evolving agents by creating an adaptive pipeline. It uses a language model agent to iteratively refi…
TabFM: A Zero-Shot Foundation Model for Tabular Data
TabFM is a novel foundation model for tabular data that leverages in-context learning for zero-shot predictions, eliminating the need for task-specific tuning. Trained on synthetic…
Effective Dense Retrieval using Only In-Context Examples
This paper introduces RICE, a training-free method to make decoder-only LLMs effective dense retrievers. RICE prompts the LLM with in-context examples that establish a shared conte…
The Town Square
DraftKings is employing AI to identify and target chronic gamblers with personalized advertising, raising concerns about exacerbating addiction.
Workshops
OpenShell is a secure and private runtime environment designed to enable the safe and reliable operation of autonomous AI agents.
Hindsight is an AI agent memory system that learns from past experiences to improve future decision-making and performance.
