AI Research

Decision Context: Persistent Behavioral Learning for AI Agents

LLM agents do not learn from corrections across sessions. A user fixes the same mistake at the start of every conversation. Existing agent memory systems primarily handle facts, such as preferences, entities, and conversational history, rather than procedural knowledge. We present Forge Decision Context (forge_dc), a…

By Nima Vahdat, Pashootan VaezipoorarXiv cs.AINov 9, 20261 min read

IWIBench: Evaluating Gradient-Free Model Driven Intra-weight Injection

Intra-weight injection lets one model change another model's behaviour by editing its weights directly, without gradients. Such edits can range from altering lexical associations to enforcing output formats or updating factual knowledge. Despite growing interest in these approaches, there has been no systematic way to…

By Chris von Csefalvay, Pranav Doma, Achyuthan Unni Krishnan, Tam\'as F\"oldiarXiv cs.AINov 9, 20261 min read

Pdb or Not to Be: Comparing Debugging Interfaces With Pass$_{X}$@$k$

Interactive debuggers are indispensable to human software development, yet coding agents overwhelmingly rely on edit-execute-observe loops, using common bash tools, test scripts, and print statements to debug via repeated shell commands. Stepping through a debugger provides live access to runtime state, which may…

By Ryan Magnuson, Ellie Kitanidis, Ariel LeearXiv cs.AINov 9, 20261 min read

ChainFlow: Few-Step Latent Flow Matching for Speculative Decoding

Speculative decoding has become a standard way to accelerate LLM inference: a lightweight drafter proposes tokens that the target verifies in one parallel pass. Existing drafters face trade-offs that limits their speedups: autoregressive drafters generate tokens one at a time, so drafting cost grows with draft length…

By Selim Aktas, Yusuf Erdem Erdem, Ahmed Zeer, Himmet Toprak Kesgin, Muzaffer Kaan…arXiv cs.AINov 9, 20261 min read

Transporting the Past: An Optimal Transport View of Backtracking Counterfactuals

We study backtracking counterfactual inference for Structural Causal Models (SCMs) through the lens of optimal transport. In SCMs, a factual observation generally induces a posterior distribution over exogenous variables, making counterfactual inference inherently distributional. We introduce two complementary…

By Zhangyi Liu, Pouria Fatemi, Suvrit SraarXiv cs.AINov 9, 20261 min read

Cancellation Is Not Enough: What Retries Leave Behind in an Overloaded LLM Engine

Clients and proxies in front of an LLM engine retry calls that time out. After a transient overload, these retries can keep the engine from recovering even when calls arrive below its capacity. Since the engine may keep computing for clients that have left, propagating cancellation looks like the natural remedy. In…

By Xindan Zhang, Fei WangarXiv cs.AINov 9, 20261 min read

Memory-Aware Multi-Agent Architecture with LLM-based Orchestration for Conversational Recommendation

Conversational recommender systems often treat user sessions in isolation, limiting their ability to capture how user intent evolves over time. While large language models (LLMs) have improved semantic understanding, they are typically used as isolated components, without addressing how memory, retrieval, and…

By Emilly Pitman de Castro, Vanessa Silva, Gustavo Kanno, Marcus Santos, Bruno…arXiv cs.AINov 9, 20261 min read

AlterNet: Adaptive-Depth Mixture-of-Experts with Learned Halting for Elastic Inference

Most LLM architectures have fixed compute demands determined at training time. We propose a novel architecture that combines the Mixture-of-Experts architecture with shallow experts and a novel dynamic-depth system to make the extent of a forward pass dynamically adjustable. Our approach lets the model automatically…

By Alexander KastiusarXiv cs.AINov 9, 20261 min read

Nous Research Releases Arete-27B that Cuts Qwen3.8-27B Propaganda From 22% to 0.9%

Nous Research released Arete-27B, an Apache 2.0 fine-tune of Qwen3.8-27B. On Nous’s 803-prompt eval, propaganda answers fell from 22% to 0.9% while Hermes Bench stayed flat at 65.60%. The post Nous Research Releases Arete-27B that Cuts Qwen3.8-27B Propaganda From 22% to 0.9% appeared first on MarkTechPost .

By Asif RazzaqMarkTechPostNov 8, 20264 min read

Microsoft Researcher John Langford Exits. AI Frontiers Group Declared Finished

By sreanHacker NewsNov 7, 20262 min read