react-agents

Tag

Cards List
#react-agents

Present but Rescaled: Chat-to-Agent Transfer of Additive Activation Steering

arXiv cs.LG · 2026-07-13 Cached

This paper presents the first systematic study of how additive activation steering, calibrated in single-turn chat, transfers to tool-using ReAct agents. It finds that while the injected direction reaches late layers at near-full strength across settings, the behavioral coupling varies unpredictably between models and contexts, with amplification up to 2x or attenuation, posing immediate safety concerns.

0 favorites 0 likes
#react-agents

Remember, Don't Re-read: Stateful ReAct Agents for Token-Efficient Autonomous Experimentation

arXiv cs.LG · 2026-06-16 Cached

This paper proposes replacing the stateless autoresearch pattern with a stateful ReAct agent using LangGraph, reducing per-iteration token costs from O(n) to O(1) and achieving 52-90% fewer tokens on hyperparameter tuning and code optimization benchmarks.

0 favorites 0 likes
#react-agents

Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents

arXiv cs.AI · 2026-05-25 Cached

Co-ReAct introduces a rubric-guided action-selection framework that uses rubrics as step-level guidance during inference for ReAct agents, improving trajectory quality and outperforming baselines on DeepResearchBench and SQA-CS-V2.

0 favorites 0 likes
← Back to home

Submit Feedback