Tag
InfoMem introduces a reward mechanism for training chunk-wise memory agents that evaluates final-memory utility using answer-conditioned information gain, improving long-context memory-agent performance under the same RL framework.
Proposes a goal-oriented clarification framework using Information Gain Reward to train LLM agents to ask effective clarification questions under underspecified user instructions, improving task success rate by 3.7% with minimal interaction overhead.
This paper proposes MARS, a mono-anchored multi-source reasoning framework that uses dynamic anchors to quantify information gain and regulate modality interactions during reinforcement learning with verifiable rewards, achieving 3.2% and 4.9% performance gains on GRPO and DAPO across diverse datasets.
This paper introduces CIG (Conversational Information Gain), a framework for measuring how utterances advance collective understanding in deliberative dialogues by tracking evolving semantic memory and scoring utterances on novelty, relevance, and implication scope. The authors demonstrate that memory-derived dynamics correlate better with human-perceived dialogue quality than traditional heuristics and develop LLM-based predictors for information-focused conversation analysis.