Xbench-DS
PulseAugur coverage of Xbench-DS — every cluster mentioning Xbench-DS across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New ICA framework improves AI agents' long-horizon information seeking
Researchers have developed a new framework called Information-Aware Credit Assignment (ICA) to improve reinforcement learning for agents that seek information over long horizons. ICA addresses the challenge of assigning…
-
New STAMP method improves credit assignment for deep search agents
Researchers have introduced STAMP, a novel method for improving credit assignment in deep search agents. This approach addresses the 'reward-credit mismatch' by providing targeted credit to actions that expose supportin…
-
MetaResearcher framework enhances AI research agent training
Researchers have introduced MetaResearcher, a new framework designed to enhance the training of deep research agents. This framework addresses limitations in current training methods by incorporating an Evolving Virtual…