RREDCoT: Segment-level reward redistribution for chain-of-thought reasoning via self-approximated credit assignment
RREDCoT is a new method for redistributing rewards across segments of Chain-of-Thought traces during RL fine-tuning of reasoning language models, addressing the high-variance delayed-reward problem inherent in GRPO-style training. Rather than using computationally expensive Monte Carlo sampling for intermediate state value estimation, the method uses the model itself to approximate optimal reward redistribution without additional generation passes. The paper evaluates RREDCoT against MC sampling and several attribution baselines, analyzing segmentation strategies and state value estimation. This is relevant to the active research thread on improving RL fine-tuning stability and efficiency for reasoning models.
Related guides (2)
Related events (8)
Rubric-Conditioned Self-Distillation: structured feedback for reasoning model post-training
A new arXiv preprint proposes Rubric-Conditioned Self-Distillation (RCSD), a post-training framework that replaces scalar reward signals and noisy chain-of-thought annotations with structured rubrics for fine-grained credit assignment. The method conditions a teacher model on criterion-level rubrics to provide token-level guidance on the student's own sampled trajectories, avoiding reliance on a single reference rationale. Evaluated on science reasoning benchmarks, RCSD outperforms GRPO by 1.0 points and OPSD by 0.9 points on average.
DelTA: Discriminative Token Credit Assignment for RLVR Training
DelTA introduces a discriminative token credit assignment method for reinforcement learning from verifiable rewards (RLVR) that addresses the problem of high-frequency formatting tokens dominating policy gradient updates. The method estimates per-token coefficients to amplify side-specific gradient directions and downweight shared or weakly discriminative ones, making the effective update direction more contrastive. On seven mathematical benchmarks, DelTA outperforms same-scale baselines by 3.26 and 2.62 average points on Qwen3-8B-Base and Qwen3-14B-Base respectively, with additional gains on code generation tasks.
STARE: Token-level advantage reweighting to prevent entropy collapse in GRPO-style RL training
Researchers introduce STARE, a method addressing policy entropy collapse in GRPO-style reinforcement learning from verifiable rewards (RLVR) for LLM post-training. Through first-order gradient analysis, they identify a token-level credit assignment mismatch and propose selectively reweighting advantages for entropy-critical tokens using batch-internal surprisal quantiles plus a closed-loop entropy gate. Evaluated across 1.5B–32B models on short/long chain-of-thought and multi-turn tool use tasks, STARE outperforms DAPO and other baselines by 4–8% on AIME24/25 while sustaining stable training over thousands of steps.
GGRO: Gradient-Guided Reward Optimization for inference-time LLM alignment
Researchers introduce Gradient-Guided Reward Optimization (GGRO), an inference-time alignment method that uses gradient signals from a reward model to inject 'nudging tokens' at high-uncertainty decoding steps, rather than relying on sampling-intensive re-ranking approaches like Best-of-N. The method monitors token-level entropy to detect distribution drift and steers generation trajectories directly, claiming improved robustness to reward hacking with minimal computational overhead. Experiments show gains across safety, helpfulness, and reasoning benchmarks compared to standard inference-time alignment baselines.
CoRP: Gradient-Free Consolidation of Rewarded Perturbations for LLM Post-Training
CoRP (Consolidating Rewarded Perturbations) is a gradient-free post-training operator that folds an ensemble of reward-weighted weight-space perturbations into a single deployable model, eliminating the inference-time cost of ensemble methods like RandOpt. A split-half analysis across 25 model-task pairs reveals reproducible low-rank structure in the rewarded perturbation population, which CoRP exploits via reward-weighted aggregation, compatibility-aware reweighting, and a held-out validation gate. Evaluated on five models (0.5B–8B) across math, code, and creative writing, CoRP improves the base model by 8.1 points on average, exceeds single-inference RandOpt by 6.5 points using one-tenth the perturbation budget, and recovers more than half the gain of a 50-pass majority-vote ensemble at one forward pass per test example.
CORE: Contrastive Reflection for Sample-Efficient Reasoning Improvement
CORE (Contrastive Reflection) is a non-parametric learning algorithm that improves LLM reasoning by comparing successful and unsuccessful reasoning traces to generate compact natural-language 'insights' about reasoning strategies. Across four reasoning tasks, CORE outperforms both parametric baselines (GRPO/RLVR) and non-parametric baselines (GEPA, episodic RAG, MemRL) under fixed rollout budgets, achieving comparable or better gains with as few as five training samples. The method is also more context-efficient than prompt-optimization approaches, storing learned knowledge as interpretable natural-language descriptions rather than raw traces or weight updates. The results suggest contrastive distillation of reasoning traces may be a more efficient route to self-improvement than traditional fine-tuning.
OneReason: Activating Chain-of-Thought Reasoning in Generative Recommendation Models
Researchers from the OneRec team introduce OneReason, a framework for enabling reasoning capabilities in generative recommendation models deployed across short-video, live-streaming, advertising, and e-commerce. The work identifies a key failure mode — that naive thinking-mode integration does not outperform non-thinking baselines — and diagnoses this as a deficit in two factors: itemic token perception and user behavior cognition. The proposed solution combines perception-focused pre-training, a three-level cognition-enhanced CoT format for supervised fine-tuning, and a specialize-then-unify RL training recipe.
TRACE: Tree-structured rollout budget allocation for efficient agentic RL training
TRACE (Tree Rollout Allocation for Contrastive Exploration) is a new framework for improving reinforcement learning with verifiable rewards (RLVR) in multi-turn agentic LLM settings. The method models each ReAct-style thought-action-observation turn as a distinct node, enabling budget allocation across both prompt-level and turn-level prefixes in a tree structure, rather than only at the prompt level. A shared predictor estimates conditional success probability at each anchor to guide allocation, enriching reward contrast within a fixed sampling budget. Empirically, TRACE improves Qwen3-14B multi-hop QA accuracy by 2.8 points over baselines at equal sampling cost.