Co-ReAct adds step-level rubric guidance to ReAct agents via a GRPO-trained generator using list-wise ranking rewards, yielding consistent gains on DeepResearchBench and SQA-CS-V2.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=
7 Pith papers cite this work. Polarity classification is still indexing.
representative citing papers
Validity-calibrated reasoning distillation improves transfer of reasoning skills by modulating updates based on relative local validity of next steps instead of enforcing full trajectory imitation.
o1-like models overthink easy tasks; self-training reduces compute use without accuracy loss on GSM8K, MATH500, GPQA, and AIME.
DelTA estimates token coefficients to amplify discriminative directions in token-gradient vectors, reweighting the RLVR surrogate to produce more contrastive side-wise centroids and yielding 3.26 and 2.62 point gains on math benchmarks for 8B and 14B Qwen3 models.
APCD adaptively branches LLM decoding paths based on token entropy and contrasts divergent paths to improve factual accuracy while preserving efficiency.
citing papers explorer
-
Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents
Co-ReAct adds step-level rubric guidance to ReAct agents via a GRPO-trained generator using list-wise ranking rewards, yielding consistent gains on DeepResearchBench and SQA-CS-V2.
-
Validity-Calibrated Reasoning Distillation
Validity-calibrated reasoning distillation improves transfer of reasoning skills by modulating updates based on relative local validity of next steps instead of enforcing full trajectory imitation.
-
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
o1-like models overthink easy tasks; self-training reduces compute use without accuracy loss on GSM8K, MATH500, GPQA, and AIME.
-
DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards
DelTA estimates token coefficients to amplify discriminative directions in token-gradient vectors, reweighting the RLVR surrogate to produce more contrastive side-wise centroids and yielding 3.26 and 2.62 point gains on math benchmarks for 8B and 14B Qwen3 models.
-
APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation
APCD adaptively branches LLM decoding paths based on token entropy and contrasts divergent paths to improve factual accuracy while preserving efficiency.
- AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation
- Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning