5arXiv cs.AI (Artificial Intelligence)·
TRACE-ROUTER: Task-level LLM routing for agentic workflows using contextual bandits
TRACE-ROUTER is a new routing framework that addresses a fundamental mismatch in enterprise LLM deployment: existing per-call routers cannot correctly attribute feedback to individual routing decisions in long-horizon agentic workflows. The system assigns each task to a single model at admission using a contextual bandit and updates its policy using the task's terminal reward, jointly optimizing accuracy and latency. On tau2-Bench, it outperforms latency-matched interpolation between individual models by 7-8 accuracy points; on Terminal-Bench it achieves 7.1 higher accuracy points than the strongest single-model baseline with 36% lower latency.
Related guides (3)
Related events (8)
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.
STRACE framework improves LLM agent optimization via structural trajectory analysis and causal extraction
Researchers introduce STRACE (Structural TRajectory Analysis and Causal Extraction), a framework for constructing high signal-to-noise optimization contexts for long-horizon LLM agents. At the batch level, STRACE mines failure patterns to filter redundant traces; within each trace, it performs causal localization over a textual dependency graph to isolate root-cause steps. On the formal verification benchmark VeruSAGE-Bench, STRACE achieves a 1.4× success-rate improvement (42.5% to 58.5%) over human-expert-designed agents, outperforming standard context-filtering baselines.
LongTraceRL: Reinforcement Learning for Long-Context Reasoning via Search Agent Trajectories and Rubric Rewards
LongTraceRL is a new RL training framework for improving long-context reasoning in LLMs, addressing limitations of existing RLVR methods. It constructs challenging training data using multi-hop questions from knowledge graph random walks and tiered distractors derived from search agent trajectories (high-confusability: read but uncited; low-confusability: seen but unopened). A rubric reward provides entity-level process supervision along reasoning chains, applied only to correct responses to prevent reward hacking. Experiments across three LLMs (4B–30B parameters) on five long-context benchmarks show consistent improvements over strong baselines.
TRIAGE: Role-typed credit assignment framework improves reinforcement learning for agentic tasks
TRIAGE is a new credit assignment framework for agentic reinforcement learning that augments standard GRPO by classifying action segments into semantic roles (decisive progress, useful exploration, no-progress infrastructure, regression) and applying role-conditioned process rewards. The approach addresses two structural blind spots of outcome-only credit: punishing useful exploration in failed rollouts and reinforcing redundant actions in successful ones. Evaluated on ALFWorld, Search-QA, and WebShop, TRIAGE improves success rates over GRPO and reduces environment-facing turns by 10-15%, with regression detection inside successful trajectories identified as the dominant contributor.
ROUTEBENCH: Controlled evidence that transformers develop latent algorithm routing in-context
Researchers introduce ROUTEBENCH, a diagnostic benchmark testing whether transformers can implicitly route between inductive-bias families (ridge-like, lasso-like, Huber-like, kNN-like) based on the latent data-generating regime, without changing prompt form. Dense decoder-only transformers trained from scratch at 44M–612M parameters show strong routing behavior, with a 306M model closing 80.9% of the oracle-routing gap and achieving route F1 of 84.1. Activation patching and probe controls confirm that route-relevant internal directions are decodable and functionally involved in output behavior. The results provide controlled mechanistic evidence for latent algorithm routing but explicitly do not generalize claims to pretrained LLMs or open-ended reasoning.
DIRECT: Adaptive test-time compute routing for embodied VLM planners
Researchers introduce DIRECT, a routing framework that dynamically allocates test-time compute for Vision-Language Models acting as embodied planners, using multimodal scene context to decide per-prompt how much compute to spend. Experiments on VLABench and RoboMME benchmarks show that different scaling axes (chain-of-thought depth, model size, memory history) yield qualitatively distinct gains, and that naive uniform scaling is wasteful. On a physical Franka arm, DIRECT matches or exceeds a stronger model's success rate at up to 65% lower average latency, improving the success-cost Pareto frontier.
Agora: Auction-based task allocation framework for LLM agent reasoning
Researchers introduce Agora, a framework that uses an incentive-compatible auction mechanism to dynamically route reasoning subtasks to the most capable expert models or tools, rather than relying on coarse-grained function matching. Agents bid based on 'rectified competence' to prevent overconfident solvers from capturing critical logic steps. Evaluations across five benchmarks show improvements over single-model, routing, and cascade baselines, with a controllable cost-quality trade-off via a single auction parameter.
VDAR-Router: Difficulty-aware retrieval-based LLM routing framework
Researchers introduce VDAR-Router, a training-free LLM routing framework that routes queries to appropriate models by first generating an explicit difficulty analysis of each query, then retrieving historical examples with similar difficulty profiles to estimate model suitability. The approach addresses a gap in existing routing methods that rely on surface semantics or embedding similarity without accounting for query difficulty. Experiments on three datasets show improved cost-performance trade-offs over existing baselines.