arxiv arXiv cs.LG · 51d ago · research

Marginal Advantage Accumulation for Memory-Driven Agent Self-Evolution

from English

This paper introduces Marginal Advantage Accumulation (MAA), a post-processing architecture that addresses cross-batch inconsistency in memory-driven agent self-evolution. MAA formalizes alignment and comparability as structural conditions, uses differential signals and exponential moving average to accumulate signed evidence per operation, and ensures traceability via semantic identity merging. It outperforms batch-level baselines in 14 out of 16 settings and reduces token consumption by about 75%.

Importance 3/3 Beats a top-lab benchmark New feature vs. leaders New harness with differentiators arXiv cs.LG Google DeepMind Mistral AI OpenAI AI agents Evaluation & benchmarks Training methods

Read original

arxiv arXiv cs.CL · 47d ago · 2 views

OpenBioRQ: Benchmark for Agentic Biomedical Research Faithfulness

OpenBioRQ introduces a benchmark of 12,553 unsolved biomedical research questions across 12 domains, designed to test agentic models' faithfulness and abstention. It evaluates models in a tool-using setting without answer keys, using real follow-up evidence rather than parametric knowledge, and reveals significant agentic collapse on the hardest questions where tools are no longer used despite being critical.

arxiv arXiv cs.AI · 51d ago · 1 view

Efficient and Sound Probabilistic Verification for AI Agents

A new framework enables secure, probabilistic policy enforcement for AI agents in ambiguous environments. It uses distributionally robust optimization to compute rigorous upper bounds on policy violation probabilities without assuming predicate independence. The method outperforms prior approaches on terminal and tool calling agent benchmarks, improving the security-utility trade-off.

arxiv arXiv cs.AI · 51d ago · 1 view

Task Manager Reduces Queue Latency by 14-75% at Enterprise Scale

A Task Manager introduces priority inference, related-event merging, and preemption to enable continuous operation in enterprise AI. It reduces high-priority queue latency by 14-77% and improves related-event correctness by over 20 percentage points at enterprise scale, addressing agent discovery noise as the primary bottleneck.

arxiv arXiv cs.CL · 51d ago · 2 views

AtomMem: Simple and Effective Memory System for LLM Agents

AtomMem introduces a memory system that stores high-value atomic facts from long-form interactions. It uses hierarchical event structures and temporal profiles to capture coherent episodic contexts and track evolving user attributes, enabling stable and efficient memory evolution. Experiments on the LoCoMo benchmark show AtomMem achieves state-of-the-art performance in reasoning tasks.

arxiv arXiv cs.CL · 51d ago

GEMS: Geometric Constraints Enable Multi-Semantic Superposition in LLMs

GEMS enables training-free superposition of multiple semantic directions in LLMs by addressing distributional deviation and directional interference through geometric constraints. On GSM8K, it maintains 98% accuracy with three non-mathematical directions, while unconstrained addition drops to 4%; on Wikitext-2, it increases PPL by only 2.2%.