Latest

Every published item, in order · 9845 items
Oct 27
Tomorrow 08:00, the daily lands in your inboxTelegram channel or email. Same screening as this page, no ads.
PapersBuildersSelected00:36
Salesforce Releases BehaviorBench for Predicting User Decisions

Building agents that model actual human behaviour has relied on synthetic personas, and this benchmark offers a measurable, open alternative with licensed data. Teams developing personalised assistants or recommendation agents can use it to evaluate how well their models exploit user history. The Apache-2.0 release on Hugging Face makes it directly usable without licensing friction.

Official accountSalesforce AI Research@SFResearchSource
Oct 26
PapersBuildersMulti-sourceSelected23:07
MCP-Injector shows tool faults cut agent scores 60%

Scaling up model size does not buy robustness against broken tools, so engineering effort belongs in framework-level error handling and fault-injected evals rather than bigger models. Teams shipping MCP-based agents in production should test against MCP-Injector-style failure mixes and compare their agent stack choices, since the framework mattered more than the model. The fault calibration is derived from real open-source MCP repository issues, making the findings directly reusable for benchmark design.

Event
DAIR.AI@dair_aiSource
PapersBuildersSelected21:01
PostTrainBench exposes locked strategy in LLM training agents

The failure mode is not execution but the absence of a trigger to re-open strategy decisions mid-run, a finding that reshapes how agent benchmarks should be designed. Anyone building autonomous ML or post-training agents should plan checkpoints for human strategy input rather than longer budgets. Defaults also follow the harness, not the task — Claude Code picks full-parameter SFT 71.9% of the time while Codex CLI picks PEFT/LoRA 89.5% — so tool choice itself biases your pipeline.

Event
OpenBMB@OpenBMBSource

Only the latest 2000 items are listed; for older ones see the daily archive