ReCrit frames critic interaction as a correctness-transition problem and uses quadrant-based RL rewards to improve LLM performance on scientific reasoning benchmarks by rewarding corrections and robustness while penalizing sycophancy.
A survey on multi-turn interaction capabilities of large language models
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
other 1
citation-polarity summary
verdicts
UNVERDICTED 6representative citing papers
MT-JailBench is a modular benchmark that standardizes evaluation of multi-turn jailbreaks to identify key success drivers and enable stronger combined attacks.
MT-OSC condenses chat history via a one-off sequential process with a few-shot Condenser and lightweight Decider to reduce tokens and preserve LLM accuracy in multi-turn settings.
A framework integrates user language and probabilistic environment estimates into adaptive safety certificates that guarantee long-term safety for stochastic systems via probabilistic invariance.
The paper surveys human memory categories, maps them to LLM memory, and proposes a new three-dimension (object, form, time) categorization into eight quadrants to organize existing work and highlight open problems.
Proposes a multi-layer framework and agent architecture that operationalizes adaptation, coherence, continuity, and agency for longitudinal health AI agents.
citing papers explorer
-
ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning
ReCrit frames critic interaction as a correctness-transition problem and uses quadrant-based RL rewards to improve LLM performance on scientific reasoning benchmarks by rewarding corrections and robustness while penalizing sycophancy.
-
MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks
MT-JailBench is a modular benchmark that standardizes evaluation of multi-turn jailbreaks to identify key success drivers and enable stronger combined attacks.
-
MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation
MT-OSC condenses chat history via a one-off sequential process with a few-shot Condenser and lightweight Decider to reduce tokens and preserve LLM accuracy in multi-turn settings.
-
Online Adaptive Probabilistic Safety Certificate with Language Guidance
A framework integrates user language and probabilistic environment estimates into adaptive safety certificates that guarantee long-term safety for stochastic systems via probabilistic invariance.
-
From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs
The paper surveys human memory categories, maps them to LLM memory, and proposes a new three-dimension (object, form, time) categorization into eight quadrants to organize existing work and highlight open problems.
-
A Framework for Longitudinal Health AI Agents
Proposes a multi-layer framework and agent architecture that operationalizes adaptation, coherence, continuity, and agency for longitudinal health AI agents.