An evaluation framework AgentCL for continual learning in agents is presented, centered on distinguishable task streams and metrics for CL properties, and MemProbe is developed, a probing method that stores interactions, insights, and skills while filtering unreliable experiences during consolidation.
LLM-powered coding agents spend the majority of their token budget reading repository files, yet much of the retrieved code is irrelevant to the task at hand. Existing learned pruners compress this context with a single-objective sequence labeler, collapsing all facets of code relevance into one score and one transitio...
Jingjing Wang, Xiwen Chen, Wenhui Zhu et al.· 0 citations
ScaleLogic is introduced, a synthetic logical reasoning framework that offers independent control over two axes of difficulty: the depth of the required proof planning and the expressiveness of the underlying formal system.
Tianle Wang, Zhaoyang Wang, Guangchen Lan et al.· 1 citation
It is hypothesized that in long traces, hindsight reveals which steps were unnecessary more readily than which steps would have repaired the solution, and that changing the divergence, enriching or reinjecting the privileged context, and training longer only move OPSD along the same accuracy-length tradeoff.
Jaehoon Kim, Dong-Ha Lee· 4 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
BALAR (Bayesian Agentic Loop for Active Reasoning), a task-agnostic outer-loop algorithm that requires no fine-tuning and enables multi-turn interaction between an LLM agent and a user, is proposed.
Aymen Echarghaoui, Dong-Xia Wu, Emily B. Fox· arXiv.org· 1 citation
It is found that task type is a stronger predictor of acceptance than tree depth, and chat produces the highest entropy yet the highest acceptance rate, which has direct implications for domain-aware speculation budgets and draft-model selection strategies.
MMORF is presented, a framework for constructing language model-based multi-agent systems (MAS) for multi-objective retrosynthesis planning that achieves strong safety and cost metrics on soft-constraint tasks, frequently Pareto-dominating baseline routes, and outperforming state-of-the-art baselines.
Frazier N. Baker, Trieu Nguyen, Reza Averly et al.· arXiv.org· 1 citation
While multi-agent systems (MAS) excel at complex reasoning, they are vulnerable to errors that intermediate agents introduce and downstream agents build upon. Auditing intermediate messages before they propagate requires an explicit standard, yet evaluation rubrics are typically authored by domain experts or written ag...
Yutong Wang, Siyuan Xiong, Xuebo Liu et al.· 0 citations
Advances in large language models (LLMs) are driving a shift toward using reinforcement learning (RL) to train agents from iterative, multi-turn interactions across tasks. However, multi-turn RL remains challenging as rewards are often sparse or delayed, and environments can be stochastic. In this regime, naive traject...
Aladin Djuhera, Swanand Kadhe, Farhan Ahmed et al.· 0 citations
Chain-of-Thought (CoT) empowers Large Language Models (LLMs) to tackle complex problems, but remains constrained by the computational cost and early token commitments in discrete reasoning traces. Recent latent reasoning approaches attempt to optimize efficiency by performing reasoning within continuous hidden states....
Jiecong Wang, Hao Peng, Zhanyi Wang et al.· 0 citations
This work introduces What If TSF (WIT), a benchmark for evaluating whether models effectively respond to future scenarios, and shows that factual accuracy gains do not consistently translate into appropriate responses to alternative scenarios, demonstrating the need to evaluate multimodal forecasting beyond predictive...
Jin-Kwan Jang, Hyunbin Jin, Hyungjin Park et al.· 0 citations
An ARC solver is introduced, Knowledge Augmentation for Abstract Reasoning (KAAR), which encodes core knowledge priors within an ontology that classifies priors into three hierarchical levels based on their dependencies and maintains strong generalization across most LLMs.
Chao Lei, N. Lipovetzky, Krista A. Ehinger et al.· arXiv.org· 2 citations
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
